Coding Tools
GitHub Copilot Fusion launches multi-model orchestration
GitHub Changeloghigh confidence
Why it matters
- →Automates model selection to reduce developer friction and optimize API costs.
- →Demonstrates measurable performance gains by routing tasks to specialized models dynamically.
- →Sets a new standard for IDE-integrated AI agents that manage their own tooling.
GitHub has generally available Copilot Fusion, a new feature that automates model selection within its IDE ecosystem. The tool routes prompts through various underlying models using strategies like cascading or critique workflows to optimize for cost and performance. According to GitHub, the Max tier achieves coding scores comparable to Claude Code Opus 5.5 while using half the tokens and taking 40% less time per task. The feature is available across Visual Studio Code, JetBrains IDEs, and the GitHub Copilot app, with enterprise administrators retaining control over which models are accessible.
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 Copilot Adds Jira Integration and HydraFusion
GitHub Changelog · September 10, 2026 · Same story
- 2GitHub Copilot HydraFusion adds Max tier and new models
GitHub Changelog · October 14, 2026 · Same story
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
llama.cpp Releases