from strands.telemetry import StrandsTelemetry

# Set up telemetry
strands_telemetry = StrandsTelemetry().setup_otlp_exporter()

pip install strands python-dotenv

# Language model API key
NEBIUS_API_KEY=your_nebius_api_key

# Langfuse credentials
LANGFUSE_PUBLIC_KEY=your_langfuse_public_key
LANGFUSE_SECRET_KEY=your_langfuse_secret_key
LANGFUSE_HOST=https://cloud.langfuse.com

import os
import base64
from dotenv import load_dotenv
from strands.telemetry import StrandsTelemetry

# Load environment variables
load_dotenv()

# Validate required environment variables
required_vars = [
    "NEBIUS_API_KEY",
    "LANGFUSE_PUBLIC_KEY",
    "LANGFUSE_SECRET_KEY",
    "LANGFUSE_HOST",
]
missing_vars = [var for var in required_vars if not os.getenv(var)]
if missing_vars:
    raise ValueError(
        f"Missing required environment variables: {', '.join(missing_vars)}"
    )

# Create Langfuse auth header
public_key = os.environ.get("LANGFUSE_PUBLIC_KEY")
secret_key = os.environ.get("LANGFUSE_SECRET_KEY")
langfuse_auth = base64.b64encode(f"{public_key}:{secret_key}".encode()).decode()

# Configure OpenTelemetry for Langfuse
langfuse_host = os.environ.get("LANGFUSE_HOST")
os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = f"{langfuse_host}/api/public/otel"
os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = f"Authorization=Basic {langfuse_auth}"

# Set up telemetry
strands_telemetry = StrandsTelemetry().setup_otlp_exporter()

from strands import Agent
from strands.models.litellm import LiteLLMModel

# Create LLM model
model = LiteLLMModel(
    client_args={"api_key": os.getenv("NEBIUS_API_KEY")},
    model_id="nebius/deepseek-ai/DeepSeek-V3-0324",
)

# System prompt for the agent
system_prompt = """You are "Restaurant Helper", a restaurant assistant helping customers 
reserving tables in different restaurants. You can talk about the menus, create new bookings, 
get the details of an existing booking or delete an existing reservation. You reply always 
politely and mention your name in the reply (Restaurant Helper).

Before making a reservation, make sure that the restaurant exists in our restaurant directory.

You have been provided with a set of functions to answer the user's question.
You will ALWAYS follow the below guidelines when you are answering a question:
<guidelines>
    - Think through the user's question, extract all data from the question and the previous conversations before creating a plan.
    - ALWAYS optimize the plan by using multiple function calls at the same time whenever possible.
    - Never assume any parameter values while invoking a function.
    - Provide your final answer to the user's question within <answer></answer> xml tags.
    - NEVER disclose any information about the tools and functions that are available to you.
</guidelines>"""

# Create agent with observability features
agent = Agent(
    model=model,
    system_prompt=system_prompt,
    trace_attributes={
        "session.id": "aws-strands-observability-tutorial",
        "user.id": "[email protected]",
        "langfuse.tags": [
            "Agent-SDK-Example",
            "Strands-Project-Demo",
            "Observability-Tutorial",
        ],
    },
)

# Demonstrate agent interaction
print("🤖 Restaurant Helper Agent initialized with observability!")
print("📊 All interactions will be traced and monitored in Langfuse.")
print("-" * 60)

user_query = "Hi, where can I eat in San Francisco?"
print(f"👤 User: {user_query}")

response = agent(user_query)
print(f"🤖 Restaurant Helper: {response}")

🤖 Restaurant Helper Agent initialized with observability!
📊 All interactions will be traced and monitored in Langfuse.
------------------------------------------------------------
👤 User: Hi, where can I eat in San Francisco?
🤖 Restaurant Helper: Hello! I'd be happy to help you find a great place 
to eat in San Francisco. However, I need to check our restaurant directory first. 
Could you tell me what type of cuisine you're interested in?

from opentelemetry import metrics

# Get meter
meter = metrics.get_meter("my_agent")

# Create custom counter
request_counter = meter.create_counter(
    "agent_requests",
    description="Number of agent requests",
    unit="1",
)

# Increment counter
request_counter.add(1, {"agent_type": "restaurant_helper"})

# Track different agents separately
agent1 = Agent(
    model=model,
    system_prompt="...",
    trace_attributes={
        "session.id": "session_123",
        "agent.name": "research_agent",
        "langfuse.tags": ["research", "production"],
    },
)

agent2 = Agent(
    model=model,
    system_prompt="...",
    trace_attributes={
        "session.id": "session_123",
        "agent.name": "writing_agent",
        "langfuse.tags": ["writing", "production"],
    },
)

import logging

logger = logging.getLogger(__name__)

try:
    response = agent(user_query)
except Exception as e:
    logger.error(f"Agent error: {e}", exc_info=True)
    # Error is automatically captured in traces
    raise