copilot-chat

Subscribe to all “copilot-chat” posts via RSS or follow GitHub Changelog on Twitter to stay updated on everything we ship.

→ ~ cd github-changelog
→ ~/github-changelog|main git log main
showing all changes successfully

Announcing the Public Beta of GitHub Copilot Extensions 🎉

Copilot Extensions header image

GitHub Copilot Extensions are now available in public beta 🚀 to all GitHub Copilot users and open for any developer or organization to create extensions. Alongside, we’re introducing a comprehensive Copilot Extensions Toolkit,
designed to equip developers by centralizing the information they need
to build quality extensions.

💡 What are Copilot Extensions and how to use them

Copilot Extensions integrate with your favorite dev tools directly into Copilot Chat across Visual Studio, VS Code, and GitHub.com (with support for JetBrains IDE coming soon!). Interact with databases, testing frameworks, deployment tools, and more — all without leaving your flow. For example:
– Docker’s extension can help you generate the right Docker assets for your project
– New Relic’s extension can help instrument your system and onboard with New Relic from within your editor

Docker extension being invoked in chat

Additionally, enterprises and organizations have the ability to build private extensions. Copilot can interact with context from your internal developer tooling, execute workflows, and adhere to your organization’s best practices.

🏁 Getting Started

To use extensions
– If you have access to Copilot through a Copilot Business or Copilot Enterprise subscription, an organization or enterprise owner needs to enable the Copilot Extensions policy for your organization or enterprise.
– Visit the GitHub Marketplace to install extensions.
– Get started with our documentation and start using extensions in Copilot Chat in GitHub.com or in the VS Code and Visual Studio editors.

To build extensions
– Access our documentation and Copilot Extensions Toolkit for tutorials and tools
– Develop your extension, and decide whether you want to keep it private to your organization or submit it to the GitHub Marketplace.
– VS Code extension developers can also add Copilot functionality to their existing VS Code extensions. Learn more here.

Share your experiences to help us improve the platform!
– Join the discussion within the GitHub Community.
– To share feedback on specific extensions, let us know in our Copilot Extensions feedback hub.
– If you’re building extensions, fill out the Extension Developer Survey for detailed feedback and feature requests.

See more

Larger context window, improved test generation, and more in VS Code’s Copilot Chat

VS Code August recent updates

Since last month’s upgrade to GPT-4o, we now increased the available Chat context, so you can reference larger files and have longer chat conversations with GitHub Copilot Chat in VS Code. Additionally, you can now click Attach Context in Inline and Quick Chat to add more relevant context to your queries.

This month’s release also brings the following improvements to Copilot Chat in VS Code:

  • Easily generate tests using the Generate Tests using Copilot action or the /tests slash command. Copilot will now update and append tests to existing files or create a new test file if none exists. Learn more.

  • Revisit previous chat sessions with the Show Chats button. Sessions now have AI-generated names and can be manually renamed. Entries are sorted by the date of the last request and grouped by date buckets. Learn more.

  • Provide specifics on unsatisfactory Chat responses by selecting the Thumbs down button. A dropdown with detailed options helps you pick a problem type or report it as an issue to us, helping us improve Copilot. Learn more.

  • Code Actions now have clearer names: Generate Tests using Copilot and Generate Documentation using Copilot. Just place the cursor on an identifier and choose the action. Learn more.

Experimental New Features

Experimental settings are available in VS Code to gather your feedback and influence the future development of Copilot. Share your thoughts in our issues.

Check out the full release notes for VS Code’s August release (version 1.93) for more details and to learn more about the features in this release.

See more

GitHub Copilot Chat and pull request summaries are now powered by GPT-4o

Copilot Chat and pull request summary generation now use GPT-4o, bringing the performance of OpenAI’s latest flagship model to all developers.

Copilot Chat is available in Visual Studio, VS Code, JetBrains IDEs, GitHub Mobile apps, and GitHub.com.

To use the new GPT-4o model in your IDE, ensure you are using at least the minimum version of Copilot Chat specified here:

What this means for Copilot users

With this upgrade to GPT-4o, Copilot users will experience the following benefits:

  1. Faster response times – up to 55% faster TTFT (time to first byte)
  2. More accurate and reliable Copilot Chat responses – our testing showed a 60% increase in user satisfaction.

Commitment to quality

The upgrade process focused on our unwavering commitment to quality, safety, and security. Here’s what that entailed:

  1. Offline and online evaluation: We performed rigorous offline and online testing to ensure the model brings tangible benefits to users. This involved thorough benchmarking and running simulations of real-world software development scenarios to validate the improved performance and accuracy of GPT-4o.
  2. Red teaming: To preemptively address any potential safety issues, we conducted extensive red teaming exercises. These tests challenged the model to ensure it meets our high standards for safety and reliability in diverse coding environments.

We can’t wait to see what you create with the new GPT-4o-powered Copilot!

Let us know your feedback and join the discussion within the GitHub Community.

Happy coding!

See more

GitHub Copilot knowledge bases available in Visual Studio (preview)

GitHub Copilot Enterprise subscribers in Visual Studio can now use Copilot Chat to get answers enriched with context from Copilot knowledge bases. To try out this functionality, you’ll need to be running Visual Studio 17.11 Preview 3 or later.

You can access a knowledge base from any Copilot Chat conversation by typing @github, pressing the # key, selecting a knowledge base from the autocomplete, and then entering your question. Copilot will respond, using the Markdown documentation in your knowledge base as context for its answer.

For more details, check out the docs for Copilot Chat in Visual Studio. To try Copilot Chat yourself, download the extension.

See more

New Copilot Enterprise features in VS Code (preview)

GitHub Copilot Enterprise users in Visual Studio Code can now get answers from Copilot Chat enriched with context from Copilot knowledge bases and Bing search results.

To get started, make sure you’re running the latest release of the GitHub Copilot Chat extension for VS Code, and then check out the docs.

Access your Copilot knowledge bases

You can now access your knowledge bases from any Copilot Chat conversation in VS Code by typing @github #kb, selecting a knowledge base from the list, and then entering your question.

Copilot will respond, using the Markdown documentation in your knowledge base as context for its answer. This allows Copilot Enterprise users to combine search results and internal documentation with editor context using existing chat variables like #file and #selection.

Search with the context of the web

GitHub Copilot can now search Bing within chat conversations in VS Code to answer questions and find information outside of its general knowledge or your codebase.

To get answers enriched with Bing search results, start your message with @github. Copilot will intelligently decide when to use Bing – or you can ask it to run a search by adding #web to your query. You can ask questions like @github What is the latest LTS version of Node.js?.

Bing search is only available if enabled by an administrator – for more details, see “Enabling GitHub Copilot Enterprise features”.

See more

New Copilot Enterprise features in Visual Studio (preview)

GitHub Copilot Enterprise subscribers in Visual Studio can now use Copilot Chat to get answers enriched with context from their entire repository (not just open tabs!) and Bing search results.

To try out this functionality, install Visual Studio 17.11 Preview 2, and then check out the docs.

Get answers from across your entire codebase

Copilot Chat can now answer questions with understanding of your full repository, not just the tabs you have open. Index your repository on GitHub.com, and then ask a question mentioning @github. You can ask questions like @github Where is device detection implemented?.

Search with the context of the web

GitHub Copilot can now search Bing to find information outside of its general knowledge or your codebase. When you mention @github, Copilot will intelligently decide when to use Bing. You can ask questions like @github What are the breaking changes in Next.js v14?.

Bing search is only available if enabled by an administrator – for more details, see “Enabling GitHub Copilot Enterprise features”.

See more

GitHub Copilot Chat General Availability in JetBrains IDE

GitHub Copilot Chat in JetBrains IDEs is now generally available

Following our Private Beta, we are thrilled to announce Copilot Chat in JetBrains IDEs is now generally available (GA) for all our Copilot Individual, Business, and Enterprise customers.

Driven by GPT-4, GitHub Copilot Chat provides instant guidance directly within various JetBrains IDEs, such as PyCharm, IntelliJ IDEA, WebStorm, Rider, and more. This contextually-aware tool tailors suggestions to your specific coding tasks and even allows explicitly adding files for reference. It empowers developers to innovate efficiently by assisting with complex concepts, code explanations, unit testing, and many more use cases, all while effortlessly adjusting to your preferred language style.

How to get started?

If you were already using Private Beta:
– No further action is required. You can continue using the chat feature as usual.

If you haven’t enabled Chat and want to use GitHub Copilot Chat in JetBrains IDEs

  • Copilot Individual users: You automatically have access to the chat within JetBrains IDEs.
  • Copilot Business and Enterprise users: Your organization admins will need to grant you access to Copilot chat in IDEs. Once you have access, please consult our getting started guide

How to give us your feedback?

We are dedicated to continuous improvement and innovation. Your feedback remains a crucial part of our development process, and we look forward to hearing more about your experiences with GitHub Copilot Chat for JetBrains IDEs. Please use this link to share your feedback or ideas on how to improve the product.

Join the discussion within GitHub Community.

See more

VS Code Copilot Chat January 2024 (version 0.12)

Copilot enhancements in Visual Studio Code

We have introduced several features to the Copilot Chat extension in Visual Studio Code. These updates, available in Visual Studio Code 1.86 and the latest Copilot Chat extension 0.12, aim to provide a more streamlined and interactive coding experience. From new context variables that offer more control over the context you provide to Copilot, to expanded voice control capabilities, these updates are designed to improve your interaction with Copilot. Let’s take a closer look at these new features.

Context variables

You can use context variables to provide additional context to your questions in chat by using the # symbol. We have introduced two new context variables: #file and #editor to give you more control to specify that context.

The #file variable lets you reference specific files from your workspace in your chat prompt. This helps make the answers from Copilot Chat more relevant to your code by providing context about the file you are working with. You can ask questions like “Can you suggest improvements to #file:package.json?” or “How do I add an extension in #file:devcontainer.json?”. By using the #file variable, you can get more targeted and accurate responses from Copilot.

image

With the #editor context variable, you have control over whether to include the visible code of the active editor in your prompt to Copilot Chat. Previously, this information was automatically included when you hadn’t selected text in the editor. Now, you can choose to explicitly add the visible code to the context or omit it for more general questions.

image

The #selection context variable already enabled you to focus Copilot’s suggestions on the specific code you select in the editor. By combining the #file, #editor, and #selection variables, you have full control over the context you provide to Copilot Chat, ensuring that you receive the most relevant and helpful answers.

Inline chat

We also added several features, such as Copilot Code Actions and an updated live mode, to make your Copilot inline chat experience more productive.

As you’re writing and iterating over your code, you can now invoke Copilot through Code Actions (light bulb) on a specific line in the editor. This functionality gives you direct and targeted access to Copilot to improve your code. When there is an error in the code, you can use the sparkle Code Action to let Copilot explain the error or propose a fix.

Image

With the updated inline chat live mode, you can now see and evaluate the suggested code modifications in-place in the editor. Additionally, you have the option to drill through to the inline diff editor to compare the proposed changes against the original code.

Responsible AI

We emphasize responsible usage of AI, especially when it comes to source code. We’ve added a new setting that asks users for confirmation before saving code that was generated by Copilot. This ensures that users have control over the code generated by Copilot and can review it before saving.

This setting, inlineChat.acceptedOrDiscardBeforeSave, is enabled by default. When the setting is enabled, a file save will wait for the user to accept or discard any pending inline chat session. This also applies when Auto Save is enabled, which will be temporarily turned off until inline chat has ended.

Image

Enhancing voice interactions

We have further enhanced voice interactions in VS Code by giving you more flexibility and options for initiating voice interactions.

Now, you can use the “Hey Code” voice command to start a voice session with Copilot Chat. You can choose whether you want this voice command to open the Chat view, inline chat in the editor, quick chat, or choose dynamically based on where the focus is.

To enable this voice command, make sure to install the GitHub Copilot Chat and VS Code Speech extensions. Once installed, you can enable the “Hey Code” voice command in the accessibility.voice.keywordActivation setting.

In addition, you can accelerate voice input for chat by using the “hold to speak” mode: press and hold the keybinding for inline chat and voice recording automatically starts. As soon as you release the keys, the request is sent to Copilot.

Besides these main features, you can also explore our other exciting new preview features.

See more

GitHub Copilot Chat now generally available for organizations and individuals

GitHub Copilot Chat now generally available for organizations and individuals

Recently, we announced that GitHub Copilot Chat in IDEs is now generally available for both Visual Studio Code and Visual Studio, and is included in all GitHub Copilot plans alongside the original GitHub Copilot productivity boosting code completion capabilities. It is also available at no cost to verified teachers, students, and maintainers of popular open source projects. As of now, GitHub Copilot Chat is still in the private beta for JetBrains IDEs.

If you’ve been using Copilot Chat in public beta or have already provided access to your development team, no additional actions are required. There’s also no need to install any additional extensions; Copilot chat extension is bundled together with the Copilot extension.

Enterprise and organization administrators can grant their development teams access to Copilot Chat by enabling the Copilot Chat setting for their users.

Please check out our guide for getting started with Copilot chat.

Looking forward to hearing about how you’re putting it to use!

Join the discussion within GitHub Community.

See more