Coding Tools
GitHub Copilot HydraFusion adds Max tier and new models
GitHub Changeloghigh confidence
Why it matters
- →Orchestrating multiple frontier models reduces reliance on single-model hallucinations.
- →Tailored reasoning effort balances speed during drafting with accuracy during review.
- →Direct workspace inspection in Critique workflows improves context awareness for code changes.
GitHub has updated its HydraFusion orchestration tool with a new 'Max' tier and an expanded model pool including Claude Opus 5.5 and GPT-6 variants. The update refines the Cascade and Critique workflows by introducing explicit judging steps and parallel critic models to inspect workspace changes directly rather than relying on text summaries. HydraFusion Max applies higher reasoning effort to demanding tasks while maintaining token efficiency through staged processing. Both versions remain in research preview for Copilot Pro, Business, and Enterprise users across VS Code, the GitHub app, and CLI.
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
What happened next
- 2GitHub Copilot Fusion launches multi-model orchestration
GitHub Changelog · October 28, 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