🚀 Upgrade Fraud Detection Workflow to current version Agent Framework 1.0.0b260130

README.md

@@ -32,10 +32,11 @@ Welcome to the official repository for the Microsoft AI Agentic Workshop! This r
 ## Key Features  
 
 - **[Microsoft Agent Framework](https://github.com/microsoft/agent-framework) Integration** - Single-agent, multi-agent Magentic orchestration, and handoff-based domain routing with MCP tools. [Pattern guide →](agentic_ai/agents/agent_framework/README.md)
-- **[Workflow Orchestration](agentic_ai/workflow/)** - Pregel-style execution, checkpointing, human-in-the-loop patterns, and real-time observability. [Fraud Detection Demo →](agentic_ai/workflow/fraud_detection/)
-- **Advanced UI Options** - React frontend with streaming visualization or Streamlit for quick prototyping
+- **[Workflow Orchestration](agentic_ai/workflow/)** - Hybrid Workflow + Durable Task architecture with fan-out/fan-in topology, human-in-the-loop, and real-time observability. [Fraud Detection Demo →](agentic_ai/workflow/fraud_detection_durable/)
+- **[Observability with Application Insights](agentic_ai/observability/)** - Full tracing of agent executions, tool calls, and LLM invocations with pre-built Grafana dashboards. [Setup Guide →](agentic_ai/observability/README.md)
+- **Advanced UI Options** - React frontend with interactive workflow visualization and step-by-step tool call details
 - **[MCP Server Integration](mcp/)** - Model Context Protocol for enhanced agent tool capabilities with advanced features: authentication, RBAC, and APIM integration
-- **[Emerging Agentic Scenarios](agentic_ai/scenarios/)** - Long-running workflows, progress updates, and durable agent patterns
+- **[Agent Evaluations](agentic_ai/evaluations/)** - Evaluate agent performance with custom metrics and test datasets
 - **Agent State & History Persistence** - In-memory or CosmosDB backend for conversation history and agent state
 - **[Enterprise-Ready Reference Architecture](infra/README.md)** - Production-grade deployment with VNet integration, private endpoints, managed identity, Terraform/Bicep IaC, and GitHub Actions CI/CD  
 
@@ -46,7 +47,7 @@ Welcome to the official repository for the Microsoft AI Agentic Workshop! This r
 1. Review the [Setup Instructions](./SETUP.md) for environment prerequisites and step-by-step installation.  
 2. Explore the [Business Scenario and Agent Design](./SCENARIO.md) to understand the workshop challenge.  
 3. Check out the **[Agent Framework Implementation Patterns](agentic_ai/agents/agent_framework/README.md)** to choose the right multi-agent approach (single-agent, Magentic orchestration, or handoff pattern).
-4. Try the **[Fraud Detection Workflow Demo](agentic_ai/workflow/fraud_detection/)** to see enterprise orchestration patterns in action.
+4. Try the **[Durable Fraud Detection Workflow](agentic_ai/workflow/fraud_detection_durable/)** to see hybrid Workflow + Durable Task orchestration with human-in-the-loop.
 5. Dive into [System Architecture](./ARCHITECTURE.md) before building and customizing your agent solutions.  
 6. Utilize the [Support Guide](./SUPPORT.md) for troubleshooting and assistance.  
 

agentic_ai/applications/.env.sample

@@ -98,3 +98,20 @@ MAGENTIC_MAX_ROUNDS=10
 # 0 = no context transfer (domain isolation)
 # N = transfer last N turns (1 turn = user message + assistant response)
 HANDOFF_CONTEXT_TRANSFER_TURNS=-1
+
+############################################  
+#     Application Insights Observability   #  
+############################################  
+# Connection string from Azure Portal > Application Insights > Overview > Connection String
+# APPLICATIONINSIGHTS_CONNECTION_STRING="InstrumentationKey=xxx;IngestionEndpoint=https://xxx.in.applicationinsights.azure.com/;LiveEndpoint=https://xxx.livediagnostics.monitor.azure.com/"
+
+# Enable sensitive data in traces (prompts, responses) - DEV ONLY!
+# ENABLE_SENSITIVE_DATA=true
+
+# Service name for telemetry (appears in Application Insights and Grafana)
+# OTEL_SERVICE_NAME="contoso-agent"
+
+# Grafana Dashboards (after setting up Azure Managed Grafana):
+# - Agent Overview: https://aka.ms/amg/dash/af-agent
+# - Workflow Overview: https://aka.ms/amg/dash/af-workflow
+

agentic_ai/applications/backend.py

@@ -15,6 +15,9 @@
 from pathlib import Path  
 from typing import Dict, List, Any, Optional, Set, DefaultDict
 from collections import defaultdict
+
+# Add parent directory to path for observability module
+sys.path.insert(0, str(Path(__file__).parent.parent))
 
 import httpx
 import jwt
@@ -29,10 +32,29 @@
 from dotenv import load_dotenv  
 
 # ------------------------------------------------------------------  
-# Environment  
+# Environment (load first so observability can read connection string)
 # ------------------------------------------------------------------  
 load_dotenv()  # read .env if present  
 
+# ------------------------------------------------------------------  
+# Observability (must be before any agent imports)
+# ------------------------------------------------------------------  
+from observability import setup_observability
+
+# Initialize Application Insights tracing if configured
+# All agents (single, reflection, handoff, etc.) are automatically traced
+_observability_enabled = setup_observability(
+    service_name="contoso-agent-backend",
+    enable_live_metrics=True,
+    enable_sensitive_data=os.getenv("ENABLE_SENSITIVE_DATA", "false").lower() in ("1", "true", "yes"),
+)
+if _observability_enabled:
+    logging.getLogger(__name__).info("✅ Application Insights observability enabled")
+
+# ------------------------------------------------------------------  
+# Auth Configuration
+# ------------------------------------------------------------------  
+
 # Feature flag: disable auth for local dev / demos
 DISABLE_AUTH = os.getenv("DISABLE_AUTH", "false").lower() in ("1", "true", "yes")
 

agentic_ai/applications/pyproject.toml

@@ -9,6 +9,7 @@ dependencies = [
     "azure-ai-evaluation>=1.14.0",
     "azure-ai-projects>=2.0.0b2",
     "azure-cosmos==4.9.0",
+    "azure-monitor-opentelemetry>=1.6.0",
     "fastapi==0.115.12",
     "flasgger==0.9.7.1",
     "flask==3.0.3",