Coding Tools
GitHub Copilot CLI adds whole codebase indexing for C++
GitHub Changeloghigh confidence
Why it matters
- →Persistent indexing removes the latency penalty of re-scanning large C++ projects on every interaction.
- →Enables accurate symbol resolution across deeply connected header and source files without manual configuration.
- →Makes Copilot CLI viable for complex enterprise C++ codebases that previously suffered from slow response times.
GitHub has enabled whole codebase indexing by default for C++ repositories in GitHub Copilot CLI. The feature uses the Microsoft C++ Language Server to create a persistent index of symbols, types, and file relationships across the entire project. This eliminates the latency caused by rediscovering project information for each individual request. While initial indexing requires additional time and memory, the system dynamically updates the index, providing faster code intelligence for subsequent interactions.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1GitHub Releases Copilot App for Desktop
Matt Wolfe · June 5, 2026 · Related
- 2GitHub Copilot Enhances Code Review Efficiency
GitHub Changelog · June 25, 2026 · Same story
- 3GitHub Copilot June Update for Visual Studio
GitHub Changelog · July 15, 2026 · Same story
More from GitHub Changelog
© GitHub ChangelogCoding Toolscoding
GitHub expands issue types to personal accounts
GitHub finally brings enterprise-grade planning structures to individual developers. Personal repositories now support customizable issue types and fields, allowing solo maintainers to standardize workflows with up to 25 distinct categories. This closes a long-standing gap where only organizations could enforce structured data schemas for bug tracking and feature management. The move signals that GitHub is treating personal open-source projects with the same operational seriousness as corporate codebases.
GitHub Changelog
© GitHub ChangelogCoding Toolscoding
GitHub Apps manage Copilot seats
GitHub finally lets automation control who gets Copilot access. By adding an Enterprise Copilot license management permission, apps can now assign and revoke seats programmatically across enterprise teams. This closes the loop on automated provisioning workflows that were previously blocked by API limitations. It shifts seat management from manual admin tasks to code-driven policy enforcement.
GitHub Changelog
© GitHub ChangelogCoding Toolscoding
Gemini 4 Carbon arrives in GitHub Copilot
Google’s latest reasoning model is now live inside GitHub Copilot, giving developers direct access to Gemini 4 Carbon for complex coding tasks. This integration marks a significant shift in the IDE landscape, as Google competes directly with its own cloud infrastructure and Microsoft’s Azure OpenAI services by embedding advanced models into the developer workflow. The availability across major IDEs like VS Code and JetBrains means teams can leverage specialized security-focused generation without leaving their environment. It signals that model differentiation is moving from raw benchmark scores to seamless, secure integration within daily coding routines.
GitHub Changelog
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.323 adds experimental Code Mode and plugin safety
This release quietly introduces Code Mode, an opt-in feature where Claude writes JavaScript to call its own tools, marking a shift toward more autonomous agent-like behavior within the CLI. The update also hardens the plugin ecosystem by enforcing version ranges and adding strict TypeScript type checking for hooks, which should significantly reduce instability from third-party extensions. Beyond these features, the changelog is dominated by critical fixes for authentication drift in background sessions and memory leaks when handling large files, stabilizing the tool for heavy enterprise use.
Claude Code Releases
Coding Toolscoding
llama.cpp b12336 fixes HunyuanVL crash
This release quietly patches a critical memory overflow in the mtmd module that caused crashes when loading HunyuanVL models. The issue stemmed from F64 position embeddings overflowing an F32 buffer, a subtle bug that broke multimodal inference for users relying on this specific architecture. By enforcing strict F32 requirements, llama.cpp stabilizes support for Tencent's vision-language model without adding new features or changing the core API. It’s a necessary maintenance update that keeps local multimodal workflows from breaking unexpectedly.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12343 adds qwen3.5 and ROCm 10
This release quietly extends llama.cpp’s hardware coverage with ROCm 10.0 binaries for both Linux and Windows, finally bringing AMD RDNA/CDNA users into the fold without manual compilation. The standout feature is native support for Qwen3.5 models via tensor merging during conversion, a necessary step as this new architecture gains traction in the open-source community. By shipping pre-built CUDA 13 binaries alongside the older 12.x versions, the project ensures forward compatibility with newer NVIDIA GPUs out of the box. There are no new quantization algorithms or performance breakthroughs here; it is purely an infrastructure update to keep pace with the rapidly shifting landscape of model architectures and GPU drivers.
llama.cpp Releases