Session traces and cost controls are emerging as key observability techniques for diagnosing AI agent failures, helping teams spot tool-call loops and runaway spend while preserving enough execution context for post-incident debugging.

GitHub has launched Copilot CLI into general availability, bringing generative AI directly to the terminal. Integrated with the GitHub CLI, it offers natural language command suggestions and code explanations. Recent updates introduce "agentic" workflows with Autopilot mode and GPT-5.4 support, alongside new enterprise telemetry for tracking usage across development teams.