Observability

curl http://localhost:7777/metrics

# prometheus.yml
scrape_configs:
  - job_name: 'orpheus'
    static_configs:
      - targets: ['localhost:7777']
    scrape_interval: 15s

# Queue depth by agent
orpheus_queue_depth{agent="my-agent"}

# Worker utilization
orpheus_pool_workers_busy / orpheus_pool_workers_total

# Request rate
rate(orpheus_execlog_requests_total[5m])

orpheus execlog list my-agent

TIMESTAMP   REQUEST ID      AGENT      STATE     SOURCE  DURATION
────────────────────────────────────────────────────────────────
21:31:59    67f6b220-10b... my-agent   COMPLETED http    234ms
21:31:50    67f6b220-10b... my-agent   STARTED   http    -
21:31:50    67f6b220-10b... my-agent   QUEUED    http    -

# View HTTP requests only
orpheus execlog list my-agent --source http

# View MCP (agent-to-agent) requests only
orpheus execlog list my-agent --source mcp

# See what agent-router did (HTTP)
orpheus execlog list agent-router --source http

# See what calculator-python received (MCP)
orpheus execlog list calculator-python --source mcp

curl http://localhost:7777/metrics

# All logs for an agent
curl "http://localhost:7777/v1/execlog?agent=my-agent"

# Filter by source
curl "http://localhost:7777/v1/execlog?agent=my-agent&source=mcp"

# Filter by state
curl "http://localhost:7777/v1/execlog?agent=my-agent&state=FAILED"

name: my-agent
runtime: python3
module: agent.py
entrypoint: handler

telemetry:
  enabled: true
  labels:
    team: platform
    tier: production
    use_case: rag

orpheus_queue_depth{agent="my-agent",team="platform",tier="production"}