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.

Fable 5.1 is generally available in the GitHub Copilot app, CLI and VS Code, with GitHub citing long running coding tasks and deep codebase research. Unlike other Claude models in Copilot it requires data retention by default so Anthropic's safety classifiers can run.

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'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 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 has added Google's Gemini 3.8 Flash to the Copilot model picker across the desktop app, CLI, and VS Code. GitHub's internal testing highlights complex terminal-based coding tasks and persistent recovery after failed steps, giving Copilot users another option for agentic shell work.

GitHub confirms GPT-6 Astra, OpenAI's long-horizon agentic coding model, is now generally available in Copilot's app, CLI, and editor integrations, with internal tests showing stronger performance on extensive coding jobs in fewer steps.

Release notes for github-mcp-server v1.12.0: new governance tools for repository rulesets and custom properties, lazily-evaluated feature flags, safer write operations (pinned merge HEADs, SHA recovery), and richer PR review/discovery support for agents.