ENHE AI
AI NewsGitHub Copilot CLIAI NewsCopilot BYOKAI ToolsGitHub Copilot appAuto Publishing

GitHub Copilot CLI GA Brings AI Coding Agents Deeper Into Terminal Workflows

GitHub made the redesigned Copilot CLI terminal interface generally available and added BYOK model-provider support to the Copilot app on June 23, 2026.

ENHE AI5 min0 views
GitHub Copilot CLI GA Brings AI Coding Agents Deeper Into Terminal Workflows

Key takeaways

GitHub announced on June 23, 2026 that the redesigned terminal interface for GitHub Copilot CLI is generally available. The interface adds terminal tabs for sessions, gists, issues and pull requests, plus in-session configuration for MCP servers, skills and plugins. On the same day, the GitHub Copilot app added BYOK support for model providers including OpenAI, Azure OpenAI, Microsoft Foundry, Anthropic, LM Studio, Ollama and OpenAI-compatible endpoints.

GitHub Copilot CLI's redesigned terminal interface became generally available on June 23, 2026.
The interface supports terminal tabs for sessions, gists, issues and pull requests.
Users can configure MCP servers, skills and plugins from within the session.
The GitHub Copilot app also added BYOK support for cloud, local and OpenAI-compatible model providers.

GitHub announced on June 23, 2026 that the redesigned GitHub Copilot CLI terminal interface is generally available. Developers can browse gists, issues and pull requests in tabs, insert references into prompts, and ask Copilot to investigate, fix, comment on or review related work.

The update also brings tool configuration into the terminal session. GitHub says users can add or search MCP servers, toggle skills and install plugins without hand-editing configuration files.

GitHub also announced BYOK support for the Copilot app on the same date. Users can add providers such as OpenAI, Azure OpenAI, Microsoft Foundry, Anthropic, LM Studio, Ollama or any OpenAI-compatible endpoint, then choose the model for each session.

For AI tool users, the main lesson is that coding agents are becoming workflow environments. Teams should evaluate repository context, tool extensions, model routing, local models, account policies and key management together.

What this means for everyday users

For ENHE users, the update shows that AI coding agents should be evaluated as governed workflows, not just chat models. Teams need to review terminal ergonomics, repository context, MCP tools, skills, plugins, BYOK providers, local models, key storage, usage policies and cost controls.

Tools you may use

Related tutorials

Related reading

GitHub Copilot CLI GA Brings AI Coding Agents Deeper Into Terminal Workflows

GitHub announced on June 23, 2026 that the redesigned terminal interface for GitHub Copilot CLI is generally available. The interface adds terminal tabs for sessions, gists, issues and pull requests, plus in-session configuration for MCP servers, skills and plugins. On the same day, the GitHub Copilot app added BYOK support for model providers including OpenAI, Azure OpenAI, Microsoft Foundry, Anthropic, LM Studio, Ollama and OpenAI-compatible endpoints.

Google Cloud and the Philippines DICT Bring Public Sector AI Agents Into Deployment

Google Cloud and the Philippines Department of Information and Communications Technology announced an expanded multi-year collaboration in June 2026. The program includes public sector AI agents, Gemini Enterprise, Google Workspace, a cross-agency cyber defense alliance and connectivity infrastructure. For AI tool users, the case highlights governance, permissions, data grounding and measurable workflow impact.

Alibaba Cloud SMS Skill Brings AI Agents Into Messaging Operations

Alibaba Cloud SMS Skill is a concrete example of cloud product capabilities becoming callable through AI Agent Skills, with practical implications for workflow automation and account governance.

GLM-5.2 Launches With 1M Context for Long-Horizon AI Agents

Z.ai released GLM-5.2 on June 17, 2026, describing it as a flagship long-horizon model with 1M-token context, stronger coding capability, flexible reasoning effort and an MIT open-source license. The model weights are listed on Hugging Face and ModelScope, with deployment support noted for frameworks such as SGLang, vLLM, Transformers, KTransformers and Unsloth.

Desktop AI Operating Companions Are Moving Assistants Into the Execution Era

AI assistants are shifting from one-off chat interfaces toward personal AI operating companions. MCP standardizes connections to tools and data, local AI brings some capability closer to the device, and LumiOS provides a concrete desktop product example for this shift.

Claude Code Artifacts Make AI Coding Outputs Shareable Inside Organizations

Claude Code Artifacts show how AI coding tools are moving from personal terminal assistants toward team-facing deliverables with access control, audit logs, and retention policies.

Summary

GitHub Copilot CLI's GA terminal interface and Copilot app BYOK support point to a broader shift: AI coding tools are moving toward connected terminal workflows with configurable models, tools, skills and governance boundaries.

Sources