Add application file

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+__pycache__/
+*.pyc
+.env
+incidentops_env/

.gitignore

@@ -0,0 +1,2 @@
+
+.env

Dockerfile

@@ -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.
+
+# 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=incidentops_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"
+
+ENV ENABLE_WEB_INTERFACE=true
+
+# 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"]

README.md

@@ -1,11 +1,255 @@
 ---
-title: Incidentops Env
-emoji: 🌖
-colorFrom: indigo
+title: Incidentops Env Environment Server
+emoji: ⏰
+colorFrom: yellow
 colorTo: blue
 sdk: docker
 pinned: false
-license: mit
+app_port: 8000
+base_path: /web
+tags:
+  - openenv
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Incidentops 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 Incidentops Env environment is through the `IncidentopsEnv` class:
+
+```python
+from incidentops_env import IncidentopsAction, IncidentopsEnv
+
+try:
+    # Create environment from Docker image
+    incidentops_envenv = IncidentopsEnv.from_docker_image("incidentops_env-env:latest")
+
+    # Reset
+    result = incidentops_envenv.reset()
+    print(f"Reset: {result.observation.echoed_message}")
+
+    # Send multiple messages
+    messages = ["Hello, World!", "Testing echo", "Final message"]
+
+    for msg in messages:
+        result = incidentops_envenv.step(IncidentopsAction(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
+    incidentops_envenv.close()
+```
+
+That's it! The `IncidentopsEnv.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 incidentops_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
+**IncidentopsAction**: Contains a single field
+- `message` (str) - The message to echo back
+
+### Observation
+**IncidentopsObservation**: 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 Incidentops Env environment server running, you can connect directly:
+
+```python
+from incidentops_env import IncidentopsEnv
+
+# Connect to existing server
+incidentops_envenv = IncidentopsEnv(base_url="<ENV_HTTP_URL_HERE>")
+
+# Use as normal
+result = incidentops_envenv.reset()
+result = incidentops_envenv.step(IncidentopsAction(message="Hello!"))
+```
+
+Note: When connecting to an existing server, `incidentops_envenv.close()` will NOT stop the server.
+
+### Using the Context Manager
+
+The client supports context manager usage for automatic connection management:
+
+```python
+from incidentops_env import IncidentopsAction, IncidentopsEnv
+
+# Connect with context manager (auto-connects and closes)
+with IncidentopsEnv(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(IncidentopsAction(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(
+    IncidentopsEnvironment,  # Pass class, not instance
+    IncidentopsAction,
+    IncidentopsObservation,
+    max_concurrent_envs=4,  # Allow 4 concurrent sessions
+)
+```
+
+Then multiple clients can connect simultaneously:
+
+```python
+from incidentops_env import IncidentopsAction, IncidentopsEnv
+from concurrent.futures import ThreadPoolExecutor
+
+def run_episode(client_id: int):
+    with IncidentopsEnv(base_url="http://localhost:8000") as env:
+        result = env.reset()
+        for i in range(10):
+            result = env.step(IncidentopsAction(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/incidentops_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
+
+```
+incidentops_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              # IncidentopsEnv client
+├── models.py              # Action and Observation models
+└── server/
+    ├── __init__.py        # Server module exports
+    ├── incidentops_env_environment.py  # Core environment logic
+    ├── app.py             # FastAPI application (HTTP + WebSocket endpoints)
+    └── Dockerfile         # Container image definition
+```

__init__.py

@@ -0,0 +1,15 @@
+# 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.
+"""Incidentops Env Environment."""
+from .client import IncidentopsEnv
+from .models import IncidentopsAction, IncidentopsObservation
+__all__ = [
+    "IncidentopsAction",
+    "IncidentopsObservation",
+    "IncidentopsEnv",
+]
+
+

client.py

@@ -0,0 +1,55 @@
+# 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.
+
+"""Incidentops Env Environment Client."""
+from __future__ import annotations
+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 IncidentopsAction, IncidentopsObservation
+
+class IncidentopsEnv(EnvClient[IncidentopsAction, IncidentopsObservation, State]):
+    def _step_payload(self, action: IncidentopsAction) -> Dict:
+        return {"action": action.action}
+
+    def _parse_result(self, payload: Dict) -> StepResult[IncidentopsObservation]:
+        obs_data = payload.get("observation", {})
+        observation = IncidentopsObservation(
+            alert_summary=obs_data.get("alert_summary", ""),
+            severity=obs_data.get("severity", "low"),
+            likely_cause=obs_data.get("likely_cause", "unknown"),
+            hf_confidence=obs_data.get("hf_confidence", 0.0),
+            services_affected=obs_data.get("services_affected", []),
+            logs_available=obs_data.get("logs_available", False),
+            log_snippet=obs_data.get("log_snippet", ""),
+            service_healthy=obs_data.get("service_healthy", False),
+            elapsed_steps=obs_data.get("elapsed_steps", 0),
+            sla_steps_remaining=obs_data.get("sla_steps_remaining", 0),
+            action_history=obs_data.get("action_history", []),
+            available_actions=obs_data.get("available_actions", []),
+            incident_resolved=obs_data.get("incident_resolved", False),
+            wrong_escalations=obs_data.get("wrong_escalations", 0),
+            metadata=obs_data.get("metadata", {}),
+            reward=payload.get("reward", 0.0),
+            done=payload.get("done", False),
+        )
+        return StepResult(
+            observation=observation,
+            reward=payload.get("reward", 0.0),
+            done=payload.get("done", False),
+        )
+
+    def _parse_state(self, payload: Dict) -> State:
+        return State(
+            episode_id=payload.get("episode_id"),
+            step_count=payload.get("step_count", 0),
+        )
+

inference.py

@@ -0,0 +1,149 @@
+from __future__ import annotations
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+import asyncio
+import json
+import os
+from typing import List, Optional
+
+from openai import OpenAI
+
+from client import IncidentopsEnv
+from models import IncidentopsAction
+
+API_KEY = os.getenv("HF_TOKEN") or os.getenv("API_KEY") or os.getenv("OPENAI_API_KEY")
+API_BASE_URL = os.getenv("API_BASE_URL", "https://router.huggingface.co/v1")
+MODEL_NAME = os.getenv("MODEL_NAME", "Qwen/Qwen2.5-72B-Instruct")
+TASK_NAME = os.getenv("INCIDENTOPS_TASK", "incidentops")
+BENCHMARK = os.getenv("INCIDENTOPS_BENCHMARK", "incidentops_env")
+MAX_STEPS = int(os.getenv("MAX_STEPS", "12"))
+TEMPERATURE = float(os.getenv("TEMPERATURE", "0.2"))
+ENV_URL = os.getenv("ENV_URL", "http://localhost:8000")
+DIFFICULTY = os.getenv("DIFFICULTY", "easy")
+
+SYSTEM_PROMPT = """
+You are an incident-response policy.
+Choose exactly one action from the environment's available actions.
+Prefer investigation when confidence is low.
+Prefer mitigation or escalation when evidence points to a cause.
+Return only the action string.
+""".strip()
+
+
+def log_start(task: str, env: str, model: str) -> None:
+    print(f"[START] task={task} env={env} model={model}", flush=True)
+
+
+def log_step(step: int, action: str, reward: float, done: bool, error: Optional[str]) -> None:
+    print(
+        f"[STEP] step={step} action={action} reward={reward:.2f} done={str(done).lower()} error={error if error else 'null'}",
+        flush=True,
+    )
+
+
+def log_end(success: bool, steps: int, score: float, rewards: List[float]) -> None:
+    rewards_str = ",".join(f"{r:.2f}" for r in rewards)
+    print(
+        f"[END] success={str(success).lower()} steps={steps} score={score:.2f} rewards={rewards_str}",
+        flush=True,
+    )
+
+
+def choose_action(client: OpenAI, obs) -> str:
+    available = obs.available_actions or []
+    if not available:
+        return "resolve_incident"
+
+    prompt = {
+        "alert_summary": obs.alert_summary,
+        "severity": obs.severity,
+        "likely_cause": obs.likely_cause,
+        "hf_confidence": obs.hf_confidence,
+        "logs_available": obs.logs_available,
+        "log_snippet": obs.log_snippet,
+        "services_affected": obs.services_affected,
+        "elapsed_steps": obs.elapsed_steps,
+        "sla_steps_remaining": obs.sla_steps_remaining,
+        "action_history": obs.action_history,
+        "available_actions": available,
+    }
+
+    response = client.chat.completions.create(
+        model=MODEL_NAME,
+        messages=[
+            {"role": "system", "content": SYSTEM_PROMPT},
+            {"role": "user", "content": json.dumps(prompt)},
+        ],
+        temperature=TEMPERATURE,
+        max_tokens=20,
+    )
+    text = (response.choices[0].message.content or "").strip().splitlines()[0].strip()
+
+    if text in available:
+        return text
+
+    # fallback heuristics
+    if not obs.logs_available and "request_logs" in available:
+        return "request_logs"
+    if obs.likely_cause == "dns_issue" and "query_dns_status" in available:
+        return "query_dns_status"
+    if obs.likely_cause == "dependency_issue" and "query_dependencies" in available:
+        return "query_dependencies"
+    if obs.hf_confidence < 0.7 and "query_region_health" in available:
+        return "query_region_health"
+    if "resolve_incident" in available and (obs.service_healthy or obs.incident_resolved):
+        return "resolve_incident"
+    return available[0]
+
+
+async def main() -> None:
+    if not API_KEY:
+        raise RuntimeError("Missing HF_TOKEN/API_KEY/OPENAI_API_KEY")
+
+    client = OpenAI(base_url=API_BASE_URL, api_key=API_KEY)
+    env = await IncidentopsEnv.from_docker_image(os.getenv("IMAGE_NAME")) if os.getenv("IMAGE_NAME") else IncidentopsEnv(base_url=ENV_URL)
+
+    rewards: List[float] = []
+    steps_taken = 0
+    success = False
+    score = 0.0
+
+    log_start(TASK_NAME, BENCHMARK, MODEL_NAME)
+
+    try:
+        result = await env.reset(difficulty=DIFFICULTY)
+        obs = result.observation
+
+        for step in range(1, MAX_STEPS + 1):
+            if result.done:
+                break
+
+            action_name = choose_action(client, obs)
+            result = await env.step(IncidentopsAction(action=action_name))
+            obs = result.observation
+            reward = float(result.reward or 0.0)
+            done = bool(result.done)
+
+            rewards.append(reward)
+            steps_taken = step
+            log_step(step, action_name, reward, done, None)
+
+            if done:
+                break
+
+        total_reward = sum(rewards)
+        score = max(0.0, min(1.0, total_reward / 5.0))
+        success = bool(obs.incident_resolved) and score >= 0.1
+
+    finally:
+        try:
+            await env.close()
+        except Exception:
+            pass
+        log_end(success, steps_taken, score, rewards)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

models.py

@@ -0,0 +1,42 @@
+# 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 Incidentops Env Environment.
+The incidentops_env environment is a simple test environment that echoes back messages.
+"""
+
+from __future__ import annotations
+from typing import Any, Dict, List, Optional
+from openenv.core.env_server.types import Action, Observation
+from pydantic import Field
+
+class IncidentopsAction(Action):
+    action: str = Field(..., description="Incident response action to execute")
+
+class IncidentopsObservation(Observation):
+    alert_summary: str = Field(default="", description="Human-readable incident summary")
+    severity: str = Field(default="low", description="Incident severity")
+    likely_cause: str = Field(default="unknown", description="Current hypothesis for the root cause")
+    hf_confidence: float = Field(default=0.0, description="Confidence score from the parsing model")
+    services_affected: List[str] = Field(default_factory=list, description="Affected services")
+    logs_available: bool = Field(default=False, description="Whether logs are available")
+    log_snippet: str = Field(default="", description="Short evidence snippet")
+    service_healthy: bool = Field(default=False, description="Whether service is healthy")
+    elapsed_steps: int = Field(default=0, description="Steps since reset")
+    sla_steps_remaining: int = Field(default=0, description="Steps remaining before SLA breach")
+    action_history: List[str] = Field(default_factory=list, description="Actions taken so far")
+    available_actions: List[str] = Field(default_factory=list, description="Available actions")
+    incident_resolved: bool = Field(default=False, description="Whether the incident is resolved")
+    wrong_escalations: int = Field(default=0, description="Count of wrong team escalations")
+    metadata: Dict[str, Any] = Field(default_factory=dict, description="Extra debug metadata")
+    reward: float = Field(default=0.0, description="Reward returned by the last step")
+    done: bool = Field(default=False, description="Whether the episode is finished")
+
+
+

openenv.yaml

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

openenv_incidentops_env.egg-info/PKG-INFO

@@ -0,0 +1,9 @@
+Metadata-Version: 2.4
+Name: openenv-incidentops_env
+Version: 0.1.0
+Summary: Incidentops 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_incidentops_env.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+README.md
+pyproject.toml
+./__init__.py
+./client.py
+./inference.py
+./models.py
+openenv_incidentops_env.egg-info/PKG-INFO
+openenv_incidentops_env.egg-info/SOURCES.txt
+openenv_incidentops_env.egg-info/dependency_links.txt
+openenv_incidentops_env.egg-info/entry_points.txt
+openenv_incidentops_env.egg-info/requires.txt
+openenv_incidentops_env.egg-info/top_level.txt
+server/__init__.py
+server/app.py
+server/incidentops_env_environment.py

openenv_incidentops_env.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

openenv_incidentops_env.egg-info/entry_points.txt

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

openenv_incidentops_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_incidentops_env.egg-info/top_level.txt

@@ -0,0 +1 @@
+incidentops_env

pyproject.toml

@@ -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.
+[build-system]
+requires = ["setuptools>=45", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "openenv-incidentops_env"
+version = "0.1.0"
+description = "Incidentops 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 incidentops_env.server.app
+server = "incidentops_env.server.app:main"
+
+[tool.setuptools]
+include-package-data = true
+packages = ["incidentops_env", "incidentops_env.server"]
+package-dir = { "incidentops_env" = ".", "incidentops_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.
+
+"""Incidentops Env environment server components."""
+
+from .incidentops_env_environment import IncidentopsEnvironment
+
+__all__ = ["IncidentopsEnvironment"]

server/app.py

@@ -0,0 +1,56 @@
+# 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 Incidentops Env Environment.
+This module creates an HTTP server that exposes the IncidentopsEnvironment
+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
+"""
+from __future__ import annotations
+from openenv.core.env_server.http_server import create_app
+try:
+    from ..models import IncidentopsAction, IncidentopsObservation
+    from incidentops_env_environment import IncidentopsEnvironment
+except Exception:
+    from models import IncidentopsAction, IncidentopsObservation
+    from server.incidentops_env_environment import IncidentopsEnvironment
+
+app = create_app(
+    IncidentopsEnvironment,
+    IncidentopsAction,
+    IncidentopsObservation,
+    env_name="incidentops_env",
+    max_concurrent_envs=1,
+)
+
+def main(host: str = "0.0.0.0", port: int = 7860) -> None:
+    import uvicorn
+    uvicorn.run(app, host=host, port=port)
+
+if __name__ == "__main__":
+    main()

server/incidentops_env_environment.py

@@ -0,0 +1,282 @@
+# 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.
+
+"""
+Incidentops Env Environment Implementation.
+
+A simple test environment that echoes back messages sent to it.
+Perfect for testing HTTP server infrastructure.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional
+from uuid import uuid4
+
+from openenv.core.env_server.interfaces import Environment
+from openenv.core.env_server.types import State
+
+try:
+    from ..models import IncidentopsAction, IncidentopsObservation
+except Exception:
+    from models import IncidentopsAction, IncidentopsObservation
+
+
+@dataclass
+class IncidentSnapshot:
+    scenario_id: str
+    task: str
+    alert_text: str
+    hidden_truth: str
+    severity: str
+    affected_services: List[str]
+    logs_available: bool
+    log_snippet: str
+    likely_cause: str
+    hf_confidence: float
+    available_actions: List[str]
+    correct_action_sequence: List[str]
+    sla_steps: int
+    step_count: int = 0
+    resolved: bool = False
+    wrong_escalations: int = 0
+    action_history: List[str] = field(default_factory=list)
+    evidence_collected: bool = False
+    team_engaged: Optional[str] = None
+
+
+SCENARIOS: Dict[str, List[Dict[str, Any]]] = {
+    "easy": [
+        {
+            "scenario_id": "easy_001",
+            "task": "single_service_outage",
+            "alert_text": "SEV-2: payment-service latency high after deploy.",
+            "hidden_truth": "bad_deployment",
+            "severity": "high",
+            "affected_services": ["payment-service"],
+            "logs_available": True,
+            "log_snippet": "deploy at 14:32 UTC caused connection pool exhaustion",
+            "likely_cause": "bad_deployment",
+            "hf_confidence": 0.92,
+            "available_actions": ["request_logs", "rollback_deploy", "restart_service", "resolve_incident"],
+            "correct_action_sequence": ["rollback_deploy", "resolve_incident"],
+            "sla_steps": 5,
+        }
+    ],
+    "medium": [
+        {
+            "scenario_id": "medium_001",
+            "task": "dependency_failure",
+            "alert_text": "SEV-1: api-gateway 5xx errors; user-profile-service slow; no logs available.",
+            "hidden_truth": "db_timeout",
+            "severity": "critical",
+            "affected_services": ["api-gateway", "user-profile-service"],
+            "logs_available": False,
+            "log_snippet": "DB timeout errors from checkout reads",
+            "likely_cause": "dependency_issue",
+            "hf_confidence": 0.72,
+            "available_actions": [
+                "request_logs",
+                "query_dependencies",
+                "escalate_db_team",
+                "escalate_network_team",
+                "restart_service",
+                "resolve_incident",
+            ],
+            "correct_action_sequence": ["request_logs", "query_dependencies", "escalate_db_team", "restart_service", "resolve_incident"],
+            "sla_steps": 8,
+        }
+    ],
+    "hard": [
+        {
+            "scenario_id": "hard_001",
+            "task": "multi_service_root_cause",
+            "alert_text": "SEV-1: EU checkout failures. Auth and payment degraded. Logs incomplete.",
+            "hidden_truth": "dns_issue",
+            "severity": "critical",
+            "affected_services": ["auth-service", "payment-service", "checkout-service"],
+            "logs_available": False,
+            "log_snippet": "DNS query failures in EU region resolver",
+            "likely_cause": "ambiguous",
+            "hf_confidence": 0.55,
+            "available_actions": [
+                "request_logs",
+                "query_dns_status",
+                "query_region_health",
+                "rollback_deploy",
+                "restart_service",
+                "escalate_network_team",
+                "escalate_db_team",
+                "broadcast_status_page",
+                "resolve_incident",
+            ],
+            "correct_action_sequence": [
+                "query_region_health",
+                "query_dns_status",
+                "escalate_network_team",
+                "broadcast_status_page",
+                "resolve_incident",
+            ],
+            "sla_steps": 12,
+        }
+    ],
+}
+
+
+class IncidentopsEnvironment(Environment):
+    SUPPORTS_CONCURRENT_SESSIONS: bool = True
+
+    def __init__(self):
+        self._state = State(episode_id=str(uuid4()), step_count=0)
+        self._snapshot: Optional[IncidentSnapshot] = None
+        self._difficulty = "easy"
+        self._last_observation: Optional[IncidentopsObservation] = None
+
+    def _pick_scenario(self, difficulty: str) -> Dict[str, Any]:
+        scenarios = SCENARIOS.get(difficulty, SCENARIOS["easy"])
+        return scenarios[0]
+
+    def _build_observation(self) -> IncidentopsObservation:
+        assert self._snapshot is not None
+        remaining = max(self._snapshot.sla_steps - self._snapshot.step_count, 0)
+        return IncidentopsObservation(
+            alert_summary=self._snapshot.alert_text,
+            severity=self._snapshot.severity,
+            likely_cause=self._snapshot.likely_cause,
+            hf_confidence=self._snapshot.hf_confidence,
+            services_affected=self._snapshot.affected_services,
+            logs_available=self._snapshot.logs_available,
+            log_snippet=self._snapshot.log_snippet if self._snapshot.logs_available else "",
+            service_healthy=self._snapshot.resolved,
+            elapsed_steps=self._snapshot.step_count,
+            sla_steps_remaining=remaining,
+            action_history=list(self._snapshot.action_history),
+            available_actions=self._snapshot.available_actions,
+            incident_resolved=self._snapshot.resolved,
+            wrong_escalations=self._snapshot.wrong_escalations,
+            metadata={
+                "scenario_id": self._snapshot.scenario_id,
+                "task": self._snapshot.task,
+                "hidden_truth": self._snapshot.hidden_truth,
+                "team_engaged": self._snapshot.team_engaged,
+                "evidence_collected": self._snapshot.evidence_collected,
+            },
+            reward=0.0,
+            done=self._snapshot.resolved,
+        )
+
+    def _calc_reward(self, action: str) -> float:
+        assert self._snapshot is not None
+        s = self._snapshot
+
+        reward = -0.05  # small step cost
+
+        if s.action_history.count(action) > 1:
+            reward -= 0.2
+
+        if action == "request_logs" and not s.logs_available:
+            reward += 0.3
+            s.logs_available = True
+            s.evidence_collected = True
+
+        if action == "query_dependencies" and s.hidden_truth == "db_timeout":
+            reward += 0.5
+            s.likely_cause = "db_timeout"
+            s.hf_confidence = min(0.95, s.hf_confidence + 0.15)
+            s.evidence_collected = True
+
+        if action == "query_dns_status" and s.hidden_truth == "dns_issue":
+            reward += 0.5
+            s.likely_cause = "dns_issue"
+            s.hf_confidence = min(0.95, s.hf_confidence + 0.20)
+            s.evidence_collected = True
+
+        if action == "query_region_health" and s.hidden_truth == "dns_issue":
+            reward += 0.4
+            s.hf_confidence = min(0.95, s.hf_confidence + 0.10)
+
+        if action == "rollback_deploy" and s.hidden_truth == "bad_deployment":
+            reward += 1.0
+            s.resolved = True
+        elif action == "rollback_deploy":
+            reward -= 0.8
+
+        if action == "escalate_db_team" and s.hidden_truth == "db_timeout":
+            reward += 0.7
+            s.team_engaged = "db_team"
+        elif action == "escalate_db_team":
+            reward -= 0.5
+            s.wrong_escalations += 1
+
+        if action == "escalate_network_team" and s.hidden_truth == "dns_issue":
+            reward += 0.7
+            s.team_engaged = "network_team"
+        elif action == "escalate_network_team":
+            reward -= 0.5
+            s.wrong_escalations += 1
+
+        if action == "broadcast_status_page":
+            reward += 0.2 if s.step_count <= 2 else 0.05
+
+        if action == "restart_service" and s.hidden_truth in {"bad_deployment", "db_timeout"}:
+            reward += 0.8
+        elif action == "restart_service":
+            reward -= 0.2
+
+        if action == "resolve_incident":
+            if s.resolved or s.hidden_truth in {"bad_deployment", "db_timeout", "dns_issue"}:
+                if s.step_count <= s.sla_steps and (s.evidence_collected or s.team_engaged is not None or s.hidden_truth == "bad_deployment"):
+                    reward += 1.5
+                    s.resolved = True
+                else:
+                    reward -= 2.0
+            else:
+                reward -= 1.0
+
+        if s.step_count > s.sla_steps:
+            reward -= 0.5
+
+        return reward
+
+    def reset(self, difficulty: str = "easy") -> IncidentopsObservation:
+        scenario = self._pick_scenario(difficulty)
+        self._difficulty = difficulty
+        self._state = State(episode_id=str(uuid4()), step_count=0)
+
+        self._snapshot = IncidentSnapshot(**scenario)
+
+        # ✅ FORCE CLEAN (important)
+        self._snapshot.action_history = []
+
+        self._last_observation = self._build_observation()
+        return self._last_observation
+
+    def step(self, action: IncidentopsAction) -> IncidentopsObservation:  # type: ignore[override]
+        assert self._snapshot is not None
+        self._snapshot.step_count += 1
+        self._state.step_count = self._snapshot.step_count
+
+        action_name = action.action
+        self._snapshot.action_history.append(action_name)
+
+        reward = self._calc_reward(action_name)
+        done = self._snapshot.resolved or self._snapshot.step_count >= self._snapshot.sla_steps
+
+        obs = self._build_observation()
+        obs.reward = reward
+        obs.done = done
+        obs.metadata = {
+            **(obs.metadata or {}),
+            "last_action": action_name,
+            "last_reward": reward,
+        }
+        self._last_observation = obs
+        return obs
+
+    @property
+    def state(self) -> State:
+        return self._state

server/requirements.txt

@@ -0,0 +1,14 @@
+openenv[core]>=0.2.0
+fastapi>=0.115.0
+uvicorn>=0.24.0
+
+
+
+
+
+
+
+
+
+
+