GitHub Copilot CLI issue proposes per-subagent AI credit breakdown in /usage
DenDrobiazko-Apryse · ghdev · 2026-07-21
GitHub Copilot CLI issue #4207 proposes adding an itemized /usage view so users can see how AI credits are split across the main agent, each subagent invocation, custom-agent name, model, and background operations like context compaction.
The motivation is practical: when a parent agent delegates investigation, implementation, review, and testing to multiple subagents, users need to know which invocation or configured model is driving most of the session cost. The issue suggests commands such as /usage --by-agent or /usage --detailed, with the session total still shown at the end.
More from coding & agent
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26
- Hugging Face ships hf CLI updates: deduped cache saves 19GB, faster buckets, retryable GPU jobs — yb2698 · 2026-10-26