Selected Anthropic and OpenAI models are now deprecated
Deprecated Models We have deprecated the following models across all GitHub Copilot experiences including Copilot Chat, inline edits, ask and agent modes, and...
162 posts from this source
Deprecated Models We have deprecated the following models across all GitHub Copilot experiences including Copilot Chat, inline edits, ask and agent modes, and...
Import project items with a search query When creating a new project, you can now add items using a search query, in addition to importing directly from a repo...
When reviewing a pull request, it’s common to move back and forth between the “Files changed” and the “Conversation” pages just to understand the full context....
Gemini 3.1 Pro, Google’s latest agentic coding model, is now rolling out in GitHub Copilot. In early testing, this model excels on effective and efficient edit‑...
You can now use GitHub’s Copilot usage metrics APIshttps://docs.github.com/enterprise-cloud@latest/rest/copilot/copilot-usage-metrics?apiVersion=2022-11-280 to...
Overview Copilot coding agenthttps://docs.github.com/copilot/concepts/agents/coding-agent/about-coding-agent is an asynchronous, autonomous background agent. D...
Copilot coding agent supports code referencing The Copilot coding agenthttps://docs.github.com/copilot/concepts/agents/coding-agent/about-coding-agent, an asyn...
GitHub secret scanning is adding support for extended metadata checks in security configurations. This change makes it substantially easier to enable extended m...
Claude Opus 4.6 is generally available to Copilot Enterprise, Copilot Business, Copilot Pro, and Copilot Pro+. You’ll now be able to access the model in GitHub...
The problem Historically, Git hooks have been problematic in GitHub Desktop. Because Desktop ships with its own embedded Git installation especially on Windows...
New Features in npm CLI v11.10.0+ Two new features are available today in npm CLI v11.10.0+https://docs.npmjs.com/cli/v11/: - Bulk configuration for OIDC trust...
Enterprise administrators can now request and download billing usage reports in .csv format via a new REST API. With this new capability, the same billing repor...
New credential management actions Enterprise owners can now use new credential management actions to respond decisively to high‑impact security incidents in th...
Claude Sonnet 4.6, Anthropic’s latest agentic coding model, is now rolling out in GitHub Copilot. In early testing, this model excels on agentic coding and is p...
We’ve just shipped a new set of improvements to make GitHub Copilot in Eclipse smarter and easier to use. These updates bring more context options, smoother wor...
Overview Copilot coding agenthttps://docs.github.com/copilot/concepts/agents/coding-agent/about-coding-agent is an asynchronous, autonomous background agent. W...
Overview Copilot coding agenthttps://docs.github.com/copilot/concepts/agents/coding-agent/about-coding-agent is an asynchronous, autonomous background agent. Y...
The required reviewer rule for repository rulesets is now generally available, giving you granular control over who must approve changes to specific branches an...
Custom properties now support required explicit valuescustom-properties-now-support-required-explicit-values !Screenshot of a custom property configuration wit...
This update brings several improvements to GitHub Copilot in JetBrains IDEs. These include support for Agent Skills in preview, several user‑experience enhancem...
We’ve updated the GitHub status pagehttps://www.githubstatus.com/ to make incident information easier to find and more useful during an active event. The status...
Model Picker Overview Copilot Pro and Pro+ subscribers can now choose a model when starting a Copilot coding agent session in the GitHub Mobile app. This lets...
New Dependabot audit log events Two new event types are now available to track changes to Dependabot settings through your organization and enterprise audit lo...
GPT-5.3-Codex, OpenAI’s latest agentic coding model, is now rolling out in GitHub Copilot. In early testing, GPT-5.3-Codex reaches new high scores on benchmarks...