What changed
GitHub's Copilot usage API now reports configured names for custom agent components and adds a totals_by_client breakdown for model traffic from OpenCode, Claude Code, Codex, Zed, Copilot CLI, cloud agents, code review and other clients. Reports include requests, sessions, tokens, model and selection mode alongside the optional peer-comparison dashboard.
Why it matters
Administrators can see Copilot consumption outside traditional IDE telemetry and distinguish internal agent components. The same detail can expose sensitive naming or create false precision when client IDs, request counts or opt-in peer groups are treated as verified identity or productivity evidence.
What to do
Review configured names for secrets, enable the metrics policy for a test organization and reconcile one known pilot across client, session, token and billing records. Treat client labels as best-effort and keep peer comparisons out of performance reviews until privacy and governance owners approve them.
Caveat
GitHub says request_count measures model calls, not prompts, and client identity comes from a reported integration ID. Historical names are not backfilled, telemetry can undercount and peer comparisons do not establish causal productivity gains.