feat: Add CI workflows with pre-submit validation and update pytest dependencies

.github/workflows/pre-submit.yml

@@ -0,0 +1,53 @@
+name: pre-submit CI
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  pre-submit:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Install dependencies
+        run: uv sync --extra dev
+
+      - name: Start server
+        run: |
+          uv run server > server.log 2>&1 &
+          echo "SERVER_PID=$!" >> "$GITHUB_ENV"
+
+      - name: Wait for server
+        run: |
+          for _ in {1..30}; do
+            if curl -fsS -X POST http://localhost:8000/reset -H "Content-Type: application/json" -d '{}' >/dev/null; then
+              exit 0
+            fi
+            sleep 2
+          done
+          echo "Server did not become ready in time"
+          cat server.log || true
+          exit 1
+
+      - name: Run pre-submission validator
+        run: |
+          chmod +x ./pre-submission.sh
+          uv run ./pre-submission.sh http://localhost:8000 .
+
+      - name: Stop server
+        if: always()
+        run: |
+          if [ -n "${SERVER_PID:-}" ]; then
+            kill "$SERVER_PID" || true
+          fi

.github/workflows/pytest.yml

@@ -22,7 +22,7 @@ jobs:
         run: |
           python -m pip install --upgrade pip
           pip install -r requirements.txt
-          pip install pytest
+          pip install pytest pytest-asyncio
 
       - name: Run tests
         run: pytest -q

client.py

@@ -12,7 +12,10 @@ from openenv.core import EnvClient
 from openenv.core.client_types import StepResult
 from openenv.core.env_server.types import State
 
-from models import CoenvAction, CoenvObservation
+try:
+    from .models import CoenvAction, CoenvObservation
+except ImportError:
+    from models import CoenvAction, CoenvObservation
 
 
 class CoEnv(

inference.py

@@ -50,29 +50,25 @@ from typing import List, Optional
 from openai import OpenAI
 from models import CoenvAction
 from client import CoEnv
+from dotenv import load_dotenv
+load_dotenv()
 IMAGE_NAME = os.getenv("IMAGE_NAME")
 API_KEY = os.getenv("HF_TOKEN") or os.getenv("API_KEY")
 
 API_BASE_URL = os.getenv("API_BASE_URL") or "https://router.huggingface.co/v1"
 MODEL_NAME = os.getenv("MODEL_NAME") or "Qwen/Qwen2.5-72B-Instruct"
-TASK_NAME = os.getenv("MY_ENV_V4_TASK", "echo")
-BENCHMARK = os.getenv("MY_ENV_V4_BENCHMARK", "my_env_v4")
+ENV_URL = os.getenv("ENV_URL") or "http://localhost:8000"
 MAX_STEPS = 8
 TEMPERATURE = 0.7
 MAX_TOKENS = 150
 SUCCESS_SCORE_THRESHOLD = 0.1  # normalized score in [0, 1]
 
-# Max possible reward: each token contributes 0.1, across all steps
 _MAX_REWARD_PER_STEP = MAX_TOKENS * 0.1
 MAX_TOTAL_REWARD = MAX_STEPS * _MAX_REWARD_PER_STEP
 
 SYSTEM_PROMPT = textwrap.dedent(
     """
-    You are interacting with a simple echo environment.
-    Each turn you must send a message. The environment will echo it back.
-    Reward is proportional to message length: reward = len(message) * 0.1
-    Your goal is to maximize total reward by sending meaningful, substantive messages.
-    Reply with exactly one message string — no quotes, no prefixes, just the message text.
+    You are an agent interacting with an Kubernetes-like simulation environment.
     """
 ).strip()