Implementing Observability Agent Skill

┌────────────────────────────────────────────────────────┐
│          OpenTelemetry: The Unified Standard           │
├────────────────────────────────────────────────────────┤
│                                                         │
│  ONE SDK for ALL signals:                              │
│  ├── Metrics (Prometheus-compatible)                   │
│  ├── Logs (structured, correlated)                     │
│  ├── Traces (distributed, standardized)                │
│  └── Context (propagates across services)              │
│                                                         │
│  Language SDKs:                                         │
│  ├── Python: opentelemetry-api, opentelemetry-sdk      │
│  ├── Rust: opentelemetry, tracing-opentelemetry        │
│  ├── Go: go.opentelemetry.io/otel                      │
│  └── TypeScript: @opentelemetry/api                    │
│                                                         │
│  Export to ANY backend:                                │
│  ├── LGTM Stack (Loki, Grafana, Tempo, Mimir)          │
│  ├── Prometheus + Jaeger                               │
│  ├── Datadog, New Relic, Honeycomb (SaaS)              │
│  └── Custom backends via OTLP protocol                 │
│                                                         │
└────────────────────────────────────────────────────────┘

from opentelemetry import metrics

meter = metrics.get_meter(__name__)
http_requests = meter.create_counter("http.server.requests")
http_requests.add(1, {"method": "GET", "status": 200})

import structlog
from opentelemetry import trace

logger = structlog.get_logger()
span = trace.get_current_span()
ctx = span.get_span_context()

logger.info(
    "processing_request",
    trace_id=format(ctx.trace_id, '032x'),
    span_id=format(ctx.span_id, '016x'),
    user_id=user_id
)

from opentelemetry.instrumentation.fastapi import FastAPIInstrumentor

app = FastAPI()
FastAPIInstrumentor.instrument_app(app)  # Auto-traces all HTTP requests

┌────────────────────────────────────────────────────────┐
│                  LGTM Architecture                      │
├────────────────────────────────────────────────────────┤
│                                                         │
│  ┌──────────────────────────────────────────────┐      │
│  │           Grafana Dashboard (Port 3000)      │      │
│  │  Unified UI for Logs, Metrics, Traces       │      │
│  └──────┬──────────────┬─────────────┬─────────┘      │
│         │              │             │                 │
│         ▼              ▼             ▼                 │
│  ┌──────────┐   ┌──────────┐  ┌──────────┐            │
│  │   Loki   │   │  Tempo   │  │  Mimir   │            │
│  │  (Logs)  │   │ (Traces) │  │(Metrics) │            │
│  │Port 3100 │   │Port 3200 │  │Port 9009 │            │
│  └────▲─────┘   └────▲─────┘  └────▲─────┘            │
│       │              │             │                   │
│       └──────────────┴─────────────┘                   │
│                      │                                 │
│              ┌───────▼────────┐                        │
│              │ Grafana Alloy  │                        │
│              │  (Collector)   │                        │
│              │  Port 4317/8   │ ← OTLP gRPC/HTTP       │
│              └───────▲────────┘                        │
│                      │                                 │
│         OpenTelemetry Instrumented Apps                │
│                                                         │
└────────────────────────────────────────────────────────┘

import structlog
from opentelemetry import trace

logger = structlog.get_logger()
span = trace.get_current_span()
ctx = span.get_span_context()

logger.info(
    "request_processed",
    trace_id=format(ctx.trace_id, '032x'),  # 32-char hex
    span_id=format(ctx.span_id, '016x'),    # 16-char hex
    user_id=user_id
)

use tracing::{info, instrument};

#[instrument(fields(user_id = %user_id))]
async fn process_request(user_id: u64) -> Result<Response> {
    // trace_id/span_id automatically included
    info!(user_id = user_id, "processing request");
    Ok(result)
}

{job="api-service"} |= "trace_id=4bf92f3577b34da6a3ce929d0e0e4736"

python scripts/setup_otel.py --language python --framework fastapi

pip install opentelemetry-api opentelemetry-sdk \
    opentelemetry-instrumentation-fastapi \
    opentelemetry-exporter-otlp

cd examples/lgtm-docker-compose
docker-compose up -d
# Grafana: http://localhost:3000 (admin/admin)
# OTLP: localhost:4317 (gRPC), localhost:4318 (HTTP)

from opentelemetry.instrumentation.fastapi import FastAPIInstrumentor

app = FastAPI()
FastAPIInstrumentor.instrument_app(app)  # Auto-trace all HTTP requests

from opentelemetry import trace

tracer = trace.get_tracer(__name__)

with tracer.start_as_current_span("fetch_user_details") as span:
    span.set_attribute("user_id", user_id)
    user = await db.fetch_user(user_id)
    span.set_attribute("user_found", user is not None)

from opentelemetry.trace import Status, StatusCode

with tracer.start_as_current_span("process_payment") as span:
    try:
        result = process_payment(amount, card_token)
        span.set_status(Status(StatusCode.OK))
    except PaymentError as e:
        span.set_status(Status(StatusCode.ERROR, str(e)))
        span.record_exception(e)
        raise

# Test log-trace correlation
# 1. Make request to your app
# 2. Copy trace_id from logs
# 3. Query in Grafana: {job="myapp"} |= "trace_id=<TRACE_ID>"

# Validate metrics
python scripts/validate_metrics.py