GitHub Ships 4 Copilot Spending Caps, But Session Limits Still Can't Stop Mid-Response
shashib · x · 2026-08-04
GitHub rolled out four spending controls for Copilot within ten days to address enterprise concerns over unmanaged AI coding costs. Cost center assignments, per-user budgets, session limits, and credit pools have been introduced, with per-user budgets acting as a hard stop.
However, analysis points out that the session limit remains a 'soft cap.' Because usage is only calculated after a response completes, it cannot interrupt an active query. This means unattended coding agents could still rack up significant overage charges before the cap triggers.
More from coding & agent
- AI Makes Implementation Cheap, but Engineering Judgment Remains Priceless — haltakov · 2026-08-04
- Vibe-Coded Arena FPS: Dev Builds Browser 3D Game Using Multiple LLMs — rudesssolo · 2026-08-04
- Scalar Field Launches Agentic Trading Desk Connecting Research to Live Execution — ycombinator · 2026-08-04
- LangSmith LLM Gateway Enters Public Beta with BYOK and Anti-Lock-in Features — LangChain · 2026-08-04
- Vibe Coding in Virtual Reality on the Apple Vision Pro — nptacek · 2026-08-04
- Gemini Spark Update: Browser Agent Automates Complex Errands via Chrome — Rare_Bunch4348 · 2026-08-04