Agent sessions (service)

Agent sessions

serviceupdated 2026-10-13edit the YAML

The Claude Code sessions that build and run this platform, each owning one track of work and pushing through the gate. Spend and tokens are summed from per-request events; a spend alert fires above USD 40 in the trailing hour.

Owner

Stefan Coetzee

Tier

Tier 2 Keeps the platform observable and the research running: data, dashboards, search, the agents. Fixed the same day.

Lifecycle

Production

System

Agents

Dashboard

Claude Code agents (Grafana)

Current state

on the status page

Docs

Cost model
Budgets and alerts
The phantom two million
On-call and escalation

Runbooks

Counter resets from parallel sessions

SRE principles applied

Agents in production are ops work
Cost per unit of work
Every incident ends in a record
SRE is a role inside Ops
Zero trust

Each principle, how this platform applies it and where it falls short: Principles in practice.

Service level objectives

None defined. Health is read from the records listed on the status page. Why that is a gap and what closes it: Service level objectives.

Dependencies

Depends on

Observability stack
Conformity gate
SearXNG
Local LLM

Outside the catalog: Anthropic API.

Used by

No other service in this catalog.