Coding Tools
CodeQL 2.27.3 adds Python 3.15 and JSON data extensions
GitHub Changeloghigh confidence
Why it matters
- →Enables static analysis of Python 3.15 codebases before widespread adoption.
- →Provides a structured way to model LLM-generated code as untrusted data sources.
- →Simplifies configuration by allowing JSON syntax for data extensions alongside YAML.
GitHub has released CodeQL version 2.27.3, updating its static analysis engine with support for Python 3.15 features such as frozendict and Unicode 17 identifiers. The update introduces an opt-in 'ai' threat model specifically designed for LLM-generated data, enabling custom source modeling for security scans. Additionally, CodeQL now accepts JSON syntax for data extensions and adds C23 bit-precise integer support. These improvements are automatically deployed to GitHub.com users and included in GitHub Enterprise Server 3.24.
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
- 1CodeQL 2.26.0 Enhances Security with AI Detection
GitHub Changelog · July 10, 2026 · Same story
- 2Claude Code v2.1.219 Update Released
Claude Code Releases · July 25, 2026 · Background
- 3AI Tools Boost TypeScript's Dominance on GitHub
AI News · August 21, 2026 · Background
- 4Llama.cpp b10934 Release Enhances JSON Schema Handling
llama.cpp Releases · September 13, 2026 · Background
- 5Claude Code v2.1.283: Gateway hints and plugin fixes
Claude Code Releases · September 26, 2026 · Background
- 6llama.cpp fixes JSON schema enforcement in Ling 3.0
llama.cpp Releases · October 4, 2026 · Related
What happened next
- 7CodeQL 2.27.4 improves accuracy and metadata
GitHub Changelog · November 4, 2026 · Same story
More from GitHub Changelog
© GitHub ChangelogCoding Toolscoding
GitHub Copilot Code Review API and UI updates
GitHub is finally exposing Copilot code review configuration to the REST and GraphQL APIs, closing a major gap for enterprise automation. Administrators can now programmatically control review effort, enablement, and custom instructions across organizations and repositories, moving beyond manual web interface tweaks. The update also refines the user experience with compact overviews, explicit attribution of AI sources like MCP servers, and better handling of bot-authored PRs. This shift makes Copilot Review a first-class citizen in CI/CD pipelines rather than just a UI feature.
GitHub Changelog
© GitHub ChangelogCoding Toolscoding
GitHub Copilot Dashboard Adds Chat and Agent Metrics
GitHub finally stops treating chat as a passive afterthought in its enterprise analytics. By adding Copilot Chat and the VS Code Agents window to the impact dashboard, the platform now tracks nine distinct experiences instead of just seven. The rebranding of 'Passive users' to 'Chat-first users' is a semantic correction that aligns metrics with actual developer behavior rather than arbitrary adoption thresholds. This gives engineering leaders a complete picture of how AI is actually being used across their codebases, closing the visibility gap between typing commands and writing code.
GitHub Changelog
© GitHub ChangelogCoding Toolscoding
Copilot expands to JetBrains Air and Xcode
GitHub Copilot is aggressively expanding its footprint beyond VS Code, landing in JetBrains Air and Xcode’s native assistant. This move signals a shift from IDE-specific plugins to a broader platform strategy, allowing developers to use their existing subscription across major ecosystems. The release also refines agent workflows with direct PR merging and remote preview capabilities, reducing context-switching for complex tasks. While the core AI engine remains unchanged, the integration depth in Xcode and JetBrains marks a significant step toward universal coding assistance.
GitHub Changelog
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.319: MCP backgrounding and gateway controls
This release finally brings proper asynchronous handling to Model Context Protocol tasks, allowing Claude Code to offload long-running tool calls to the background instead of blocking the main thread. For enterprise users, the new pooled budget rules and JSON logging make the Claude apps gateway significantly more manageable for large teams. The update also tightens error reporting in auto mode, ensuring developers get clear reasons when actions are denied rather than silent failures. It’s a pragmatic patch that improves reliability for complex agent workflows.
Claude Code Releases
Coding Toolscoding
llama.cpp b12173 adds OpenCL repeat ops
This release quietly patches a gap in llama.cpp's OpenCL backend by adding support for the 'repeat' operation across f16, i32, i16, and bf16 types. For users relying on AMD or Intel GPUs via OpenCL rather than Vulkan or ROCm, this means fewer fallbacks to slower CPU execution for models that use these tensor operations. It’s a targeted fix that improves stability and performance on non-NVIDIA hardware without changing the core inference engine. The update also includes standard binaries for CUDA 13 and ROCm 10.0, keeping the stack current with latest driver ecosystems.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12174 adds ROCm 10 and CUDA 13
This release quietly closes the hardware gap for non-NVIDIA users by adding default support for ROCm 10.0 on both Linux and Windows, allowing AMD GPU owners to run local models without complex configuration. It also brings CUDA 13.5 builds to Ubuntu and Windows, future-proofing the toolchain for newer NVIDIA architectures while maintaining backward compatibility with CUDA 12. Apple Silicon KleidiAI is disabled in this build, a notable regression for Mac users who rely on that specific optimization. The update solidifies llama.cpp's position as the most versatile inference runtime available, covering everything from Snapdragon NPUs to Intel Arc via SYCL.
llama.cpp Releases