
GitHub has rolled out new features for Visual Studio Code, focusing on an agent-first approach to enhance developer productivity. The updates include a preview of the Agents window, which allows for streamlined task management across projects. Remote agent sessions now support continued operation even when the client disconnects. Additionally, the bring-your-own-key model support has been expanded to air-gapped environments, and session synchronization has been improved. These enhancements aim to make VS Code a more cohesive and efficient tool for developers.
Read original
© GitHub ChangelogGitHub has announced the deprecation of the GPT-4.1 model across all its Copilot experiences, including Copilot Chat and code completions. This move requires users to update their workflows and integrations to utilize supported models. Administrators need to ensure that access to alternative models is enabled through Copilot settings. This change signifies a shift in GitHub's AI strategy, potentially aligning with newer or more efficient models. Users are encouraged to consult GitHub's documentation for guidance on available models and to adjust their settings accordingly.
© GitHub ChangelogGitHub has expanded the technical preview of its Copilot app to all existing Copilot Pro, Pro+, Business, and Enterprise customers, marking a significant step in agent-native software development. The app introduces 'canvases', a new feature that allows users to interact with and verify agent work in real-time, enhancing collaboration between humans and AI agents. This release shifts the focus from traditional coding to managing and steering agent output, offering a more integrated development experience. With features like voice conversations and cloud sessions, the Copilot app aims to streamline the development process by making agent interactions more visible and actionable.
© GitHub ChangelogGitHub has made its Copilot SDK generally available, allowing developers to integrate Copilot's agentic engine into their applications with a stable API. This release means developers can now access the same runtime that powers GitHub Copilot, enabling features like planning, tool invocation, and multi-turn sessions without building their own orchestration layers. The SDK supports multiple programming languages, including a new Java integration, and offers features like OpenTelemetry tracing and flexible authentication. This marks a significant step in making AI-driven development tools more accessible and customizable for developers.
The latest update to Claude Code, version 2.1.161, brings several enhancements and bug fixes aimed at improving user experience and performance. Notably, OpenTelemetry resource attributes are now included as labels on metric datapoints, allowing for more detailed usage analysis. The update also introduces parallel tool calls, ensuring that a failed Bash command doesn't cancel other calls in the same batch. Additionally, improvements in terminal rendering performance and fixes for various bugs, such as issues with workflow animations and session management, make this a significant update for developers using Claude Code.
The latest update to Claude Code, version 2.1.162, brings a host of improvements and fixes that enhance user experience and functionality. Notably, the update addresses several permission and configuration issues, ensuring smoother startup and operation across different environments. The rebranding of Windsurf to Devin Desktop reflects a broader shift in the platform's identity. Additionally, the update improves the handling of session and messaging features, making interactions more intuitive and reliable. These changes collectively make Claude Code more robust and user-friendly, particularly for developers relying on its tools.
Wasmer has effectively utilized OpenAI's Codex, paired with GPT-5.5, to craft a Node.js runtime specifically for edge computing. This strategic use of AI has propelled their development speed to levels 10 to 20 times faster than conventional approaches. By completing the project in weeks rather than months, Wasmer showcases the transformative potential of AI-assisted coding. This development not only exemplifies the efficiency gains achievable with AI but also sets a new standard for future projects in edge computing environments. The achievement underscores the role of AI in streamlining complex development tasks and enhancing productivity.