app.py

import os
import json
import numpy as np
import gradio as gr
import requests
import pandas as pd
import datetime
from typing import List, Dict, Any
import hashlib
import asyncio

# Import enhanced modules
from models import ReliabilityEvent, EventSeverity, AnomalyResult, HealingAction
from healing_policies import PolicyEngine
from agent_orchestrator import OrchestrationManager, AgentSpecialization

# === Configuration ===
HF_TOKEN = os.getenv("HF_TOKEN", "").strip()
HF_API_URL = "https://router.huggingface.co/hf-inference/v1/completions"
HEADERS = {"Authorization": f"Bearer {HF_TOKEN}"} if HF_TOKEN else {}

# === Initialize Enhanced Components ===
policy_engine = PolicyEngine()
orchestration_manager = OrchestrationManager()
events_history: List[ReliabilityEvent] = []

# [Keep existing FAISS setup and BusinessImpactCalculator...]

class EnhancedReliabilityEngine:
    def __init__(self):
        self.performance_metrics = {
            'total_incidents_processed': 0,
            'multi_agent_analyses': 0,
            'average_processing_time': 0.0
        }
    
    async def process_event_enhanced(self, component: str, latency: float, error_rate: float,
                                   throughput: float = 1000, cpu_util: float = None,
                                   memory_util: float = None) -> Dict[str, Any]:
        """Enhanced event processing with multi-agent orchestration"""
        start_time = asyncio.get_event_loop().time()
        
        # Create event
        event = ReliabilityEvent(
            component=component,
            latency_p99=latency,
            error_rate=error_rate,
            throughput=throughput,
            cpu_util=cpu_util,
            memory_util=memory_util,
            upstream_deps=["auth-service", "database"] if component == "api-service" else []
        )
        
        # Multi-agent analysis
        agent_analysis = await orchestration_manager.orchestrate_analysis(event)
        
        # Policy evaluation
        healing_actions = policy_engine.evaluate_policies(event)
        
        # Business impact
        business_impact = business_calculator.calculate_impact(event) 
        
        # Update metrics
        processing_time = asyncio.get_event_loop().time() - start_time
        self._update_performance_metrics(processing_time)
        
        # Prepare comprehensive result
        result = {
            "timestamp": event.timestamp,
            "component": component,
            "latency_p99": latency,
            "error_rate": error_rate,
            "throughput": throughput,
            "status": "ANOMALY" if agent_analysis.get('incident_summary', {}).get('anomaly_confidence', 0) > 0.5 else "NORMAL",
            "multi_agent_analysis": agent_analysis,
            "healing_actions": [action.value for action in healing_actions],
            "business_impact": business_impact,
            "processing_metadata": {
                "processing_time_seconds": round(processing_time, 3),
                "agents_used": agent_analysis.get('agent_metadata', {}).get('participating_agents', []),
                "analysis_confidence": agent_analysis.get('incident_summary', {}).get('anomaly_confidence', 0)
            }
        }
        
        events_history.append(event)
        return result

# Initialize enhanced engine
enhanced_engine = EnhancedReliabilityEngine()

# [Keep existing UI setup, but enhance the submission function...]

async def submit_event_enhanced(component, latency, error_rate, throughput, cpu_util, memory_util):
    """Enhanced event submission with async processing"""
    try:
        # Convert inputs
        latency = float(latency)
        error_rate = float(error_rate)
        throughput = float(throughput) if throughput else 1000
        cpu_util = float(cpu_util) if cpu_util else None
        memory_util = float(memory_util) if memory_util else None
        
        # Process with enhanced engine
        result = await enhanced_engine.process_event_enhanced(
            component, latency, error_rate, throughput, cpu_util, memory_util
        )
        
        # [Keep existing table formatting...]
        
        # Enhanced output formatting
        status_emoji = "🚨" if result["status"] == "ANOMALY" else "✅"
        output_msg = f"{status_emoji} {result['status']}"
        
        # Add multi-agent insights
        if "multi_agent_analysis" in result:
            analysis = result["multi_agent_analysis"]
            output_msg += f"\n🎯 Confidence: {analysis.get('incident_summary', {}).get('anomaly_confidence', 0)*100:.1f}%"
            
            if analysis.get('recommended_actions'):
                output_msg += f"\n💡 Insights: {', '.join(analysis['recommended_actions'][:2])}"
        
        # [Keep existing business impact and healing actions display...]
        
        return (output_msg, table_output)
        
    except Exception as e:
        return f"❌ Error processing event: {str(e)}", gr.Dataframe(value=[])