GitHub

Kimi K3, Moonshot's open-weight model, reaches general availability in GitHub Copilot, hosted by Fireworks, with frontier-level agentic coding at aggressive pricing.

GitHub's prescription for the giant agent-authored pull request: break it into a stack of ordered PRs, one concern per layer, with CI validating each layer against the stack's base. The gh stack CLI creates, submits, rebases and syncs the stack; reviewers read top-down and validate bottom-up.

GitHub makes Claude Fable 5.1 generally available across Copilot surfaces for paid tiers. Unlike other Claude models it requires data retention for safety classifiers. Admins must enable a policy, and eligible enterprises get zero data retention under an exception through year end.

GitHub made Balanced depth generally available for Copilot code review alongside the existing Lite mode, with the default settable at the organization or repository level and overridable when requesting a review on a single pull request.

GitHub Skills added four interactive exercises aimed at agentic development: orchestrating specialized agents through Copilot CLI, building workflows that automate repository tasks, taking an idea to a merged PR with the Copilot app, and automating code-quality signals earlier in the loop.

Automatic model routing costs 30 percent less for Copilot Max users until September.

Copilot's recent shipping, in one place: agentic work from Slack and Teams by mentioning @GitHub, a Customize tab unifying MCP servers, plugins and skills, GA for Gemini 3.7 Flash, MAI-Code-1.1-Flash and Kimi K3, a multi-session sidebar in Copilot CLI, and on-device multilingual dictation in VS Code

GitHub temporarily pauses the Kimi K3 rollout during a GitHub Actions incident, confirming pricing of $3 per million input tokens and $15 per million output when it resumes.

A walkthrough of modernizing a ten-year-old personal React app with stacked sessions and stacked pull requests in the GitHub Copilot app: plan first, watch the one-shot attempt fail on a forgotten dev branch, then chain sessions that each build on the last, with a second model reviewing the plan.

GitHub engineers describe moving nearly all repositories to Azure under agent-driven traffic growth. Per-reference write serialization lifts throughput 3-4x across a 25ms cross-region link, and ephemeral virtual replicas backed by object storage let reads scale independently of the write quorum.

GitHub made Claude Haiku 5.5 generally available in Copilot across VS Code, Visual Studio, JetBrains, Xcode, the CLI, cloud agent and mobile for paid plans. It is aimed at subagents, quick edits and terminal work, billed at provider list pricing, with rollout gradual and admin policy control.

GitHub made Claude Sonnet 5.5 generally available in Copilot across VS Code, Visual Studio, JetBrains, Xcode, Eclipse, the CLI and the coding agent. It bills at provider list pricing, rolls out gradually, and admins manage access via model policy.

GitHub's August ship log: Copilot arrives in Slack and Microsoft Teams with CLI grade agentic actions, Gemini 3.7 Flash, MAI-Code-1.1-Flash, and Kimi K3 reach general availability, GPT-5.6 Sol drops 50 percent, Auto selection is 30 percent off for Max, and code review gains a Balanced depth.

GitHub adds a REST API endpoint for tracking a repository's star growth over time, a privacy-safe alternative now that stargazer-listing endpoints are restricted to admins and collaborators.

GitHub sits down with OpenClaw creator Peter Steinberger and core maintainers around the 2.0 release, covering how a project that grew faster than any other on the platform handled scaling pressure and security review as it became infrastructure people depend on.

GitHub details why agent-scale development strains its Spokes architecture, where every replica joins each write, and shares usage figures including 7.38B September commits. It outlines the push to decouple durability from read scale.

GitHub Copilot added OpenAI's GPT-6 Sol (balanced, agentic coding) and GPT-6 Luna (lightweight, lowest cost). Sol needs Pro+, Max, Business or Enterprise; Luna starts at Pro. Both appear in the model picker across IDEs, CLI and the cloud agent, with gradual rollout and usage-based billing.

GitHub makes Gemini 4 Argon generally available in Copilot (app, CLI and VS Code), reporting more solved tasks than prior Gemini models on every coding benchmark, with its biggest gains in Copilot CLI.

GitHub's HydraFusion research preview reaches VS Code and the Copilot app. It looks like one model but chooses among single, cascade and critique workflows across model families, with more progress transparency. Benchmark claims are in a separate post not reviewed here.

GitHub has made a three-day cooldown the default for Dependabot's non-security version update pull requests, on the reasoning that maintainers and researchers usually surface problems in a fresh release within that window. Security updates are not held back.

GitHub added Google's Gemini 3.8 Flash to the Copilot model picker for Pro, Pro+, Max, Business and Enterprise plans across the IDEs, CLI, cloud agent and app. Rollout is gradual, pricing is introductory through year end, and admins control access by policy.

GitHub Copilot makes OpenAI's GPT-6.1 Sol generally available for Pro+, Max, Business and Enterprise across VS Code, CLI, the coding agent and JetBrains. It bills at provider list pricing; GitHub reports fewer tokens and steps in early testing.

GitHub's changelog confirms Claude Opus 5.5 is available in Copilot across VS Code, Visual Studio, JetBrains, Xcode, Eclipse, the CLI, and the coding agent. It covers plan eligibility, admin model policy, usage-based pricing, gradual rollout, and output watermarking.

GitHub's September 2026 ship log covers Project HydraFusion, a multi-model orchestration preview now in the Copilot app and VS Code, new Copilot models, and a star history REST endpoint.