Add test endpoints and enable alerts on Space

hopcroft_skill_classification_tool_competition/main.py

@@ -13,6 +13,8 @@ Endpoints:
     GET  /health   - Health check
     POST /predict  - Single issue classification
     POST /predict/batch - Batch classification
+    GET  /test/500 - Trigger 500 error (Testing only)
+    GET  /test/slow - Trigger slow response (Testing only)
 """
 
 from contextlib import asynccontextmanager
@@ -20,6 +22,7 @@ from datetime import datetime
 import json
 import os
 import time
+import asyncio
 from typing import List
 
 from fastapi import FastAPI, HTTPException, Request, Response, status
@@ -484,6 +487,22 @@ async def list_predictions(skip: int = 0, limit: int = 10) -> List[PredictionRec
         )
 
 
+@app.get("/test/500", include_in_schema=False)
+async def test_500_error():
+    """Trigger a 500 error for testing alerts."""
+    raise HTTPException(
+        status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+        detail="Test 500 Error Triggered",
+    )
+
+
+@app.get("/test/slow", include_in_schema=False)
+async def test_slow_request():
+    """Trigger a slow response for testing alerts."""
+    await asyncio.sleep(3)  # Sleep for 3 seconds (alert threshold is 2s)
+    return {"message": "Slow response completed"}
+
+
 @app.exception_handler(ValidationError)
 async def validation_exception_handler(request, exc: ValidationError):
     """Handle Pydantic validation errors."""

scripts/start_space.sh

@@ -53,12 +53,18 @@ for i in {1..30}; do
 done
 
 echo "$(date) - Configuring and starting Prometheus..."
+# Copy alert rules
+cp monitoring/prometheus/alert_rules.yml /tmp/alert_rules.yml
+
 # Create a config for the space
 cat <<EOF > /tmp/prometheus.yml
 global:
   scrape_interval: 15s
   evaluation_interval: 15s
 
+rule_files:
+  - "/tmp/alert_rules.yml"
+
 scrape_configs:
   - job_name: 'hopcroft-api'
     metrics_path: '/metrics'

scripts/trigger_alerts.py

@@ -0,0 +1,33 @@
+import requests
+import time
+import sys
+
+SPACE_URL = "https://dacrow13-hopcroft-skill-classification.hf.space"
+
+def trigger_500_errors(count=20):
+    print(f"Triggering {count} 500 errors...")
+    for i in range(count):
+        try:
+            requests.get(f"{SPACE_URL}/test/500")
+            print(f"Request {i+1}/{count} sent", end="\r")
+        except Exception as e:
+            print(f"Error sending request: {e}")
+        time.sleep(0.5)
+    print("\nDone triggering 500 errors.")
+
+def trigger_slow_requests(count=10):
+    print(f"Triggering {count} slow requests...")
+    for i in range(count):
+        try:
+            requests.get(f"{SPACE_URL}/test/slow")
+            print(f"Request {i+1}/{count} sent", end="\r")
+        except Exception as e:
+            print(f"Error sending request: {e}")
+        # No sleep needed here as the request itself takes 3s
+    print("\nDone triggering slow requests.")
+
+if __name__ == "__main__":
+    print("Starting alert trigger script...")
+    trigger_500_errors()
+    trigger_slow_requests()
+    print("Check Prometheus Alerts tab: https://dacrow13-hopcroft-skill-classification.hf.space/prometheus/alerts")