監視 & 可観測性

curl http://localhost:8080/health

{
  "status": "healthy",
  "version": "0.3.0",
  "time": "2025-01-20T10:00:00Z",
  "checks": {
    "gateway": "ok"
  }
}

curl http://localhost:8080/readiness

{
  "status": "ready",
  "version": "0.3.0",
  "time": "2025-01-20T10:00:02Z",
  "checks": {
    "orchestrator": "ok"
  }
}

import requests

health = requests.get("http://localhost:8080/health").json()
print("Gateway:", health.get("status"), health.get("checks"))

ready = requests.get("http://localhost:8080/readiness").json()
print("Readiness:", ready.get("status"), ready.get("checks"))

{
  "timestamp": "2024-10-27T10:00:00Z",
  "level": "INFO",
  "service": "orchestrator",
  "task_id": "task-dev-1730000000",
  "message": "Task submitted",
  "metadata": {
    "mode": "standard",
    "estimated_cost": 0.15
  }
}

alerts:
  - name: high_error_rate
    condition: error_rate > 0.05
    action: notify
    channels: [email, slack]

  - name: budget_warning
    condition: daily_cost > 100
    action: notify
    channels: [email]

  - name: service_down
    condition: health_check_failed
    action: page
    channels: [pagerduty]

# prometheus.yml
scrape_configs:
  - job_name: 'orchestrator'
    static_configs:
      - targets: ['localhost:2112']   # Go Orchestrator /metrics

  - job_name: 'agent_core'
    static_configs:
      - targets: ['localhost:2113']   # Rust Agent Core /metrics

  - job_name: 'llm_service'
    metrics_path: '/metrics'
    static_configs:
      - targets: ['localhost:8000']   # Python LLM Service /metrics

# HELP shannon_task_total Total number of tasks
# TYPE shannon_task_total counter
shannon_task_total{status="completed"} 1234
shannon_task_total{status="failed"} 12

# HELP shannon_task_duration_seconds Task execution duration
# TYPE shannon_task_duration_seconds histogram
shannon_task_duration_seconds_bucket{le="1.0"} 100
shannon_task_duration_seconds_bucket{le="5.0"} 450

from opentelemetry import trace
from shannon import ShannonClient

tracer = trace.get_tracer(__name__)

with tracer.start_as_current_span("analyze_data"):
    client = ShannonClient()
    handle = client.submit_task(query="データセットを分析してください")
    result = client.get_status(handle.task_id)

import logging
logging.basicConfig(level=logging.DEBUG)

# Shannonが詳細ログを出力するようになります
client = ShannonClient()