Skip to main content

GitHub Copilot - Custom Instructions

I talked about custom instructions before as a way to tweak the Copilot prompt when interacting with GitHub Copilot. At that time it was rather limited and you had not much control on how it was applied.

The way it was handled was through a custom Markdown copilot-instructions.md file. This feature has further evolved and now you can specify instructions for multiple purposes:

  • Code-generation instructions - provide context specific for generating code. You can specify those instructions directly in the settings, or in a Markdown file in your workspace.

  • Test-generation instructions - provide context specific for generating tests.  You can specify those instructions directly in the settings, or in a Markdown file your workspace.

  • Code review instructions - provide context specific for reviewing the current editor selection. You can specify those instructions directly in the settings, or in a Markdown file in your workspace.

  • Commit message generation instructions - provide context specific for generating commit messages. You can specify those instructions directly in the settings, or in a Markdown file in your workspace.

Configure a specific set of instructions

  • Open the Command Palette: Press Ctrl+Shift+P (Windows/Linux) or Cmd+Shift+P (macOS) to open the Command Palette.

  • Open Settings (JSON): Type Preferences: Open Settings (JSON) and select it from the list.

  • Edit the settings.jsonfile: This will open the settings.json file where you can add or modify settings.Now we can add for example a code-generation instruction:

  • Save the file: After making your changes, save the settings.json file.

Here are the different settings that can be used:

Instruction Setting
Code-generation instructions

github.copilot.chat.codeGeneration.instructions
Test-generation instructions

github.copilot.chat.testGeneration.instructions
Code review instructions

github.copilot.chat.reviewSelection.instructions
Commit message instructions

github.copilot.chat.commitMessageGeneration.instructions

    Remark: If you define custom instructions in both the .github/copilot-instructions.md file and in settings, Copilot tries to combine instructions from both sources.

    More information

    Custom instructions when using GitHub Copilot

    Custom instructions for GitHub Copilot in VS Code

    Labels:

    Popular posts from this blog

    Podman– Command execution failed with exit code 125

    After updating WSL on one of the developer machines, Podman failed to work. When we took a look through Podman Desktop, we noticed that Podman had stopped running and returned the following error message: Error: Command execution failed with exit code 125 Here are the steps we tried to fix the issue: We started by running podman info to get some extra details on what could be wrong: >podman info OS: windows/amd64 provider: wsl version: 5.3.1 Cannot connect to Podman. Please verify your connection to the Linux system using `podman system connection list`, or try `podman machine init` and `podman machine start` to manage a new Linux VM Error: unable to connect to Podman socket: failed to connect: dial tcp 127.0.0.1:2655: connectex: No connection could be made because the target machine actively refused it. That makes sense as the podman VM was not running. Let’s check the VM: >podman machine list NAME         ...
    Read more

    Cache stampede: when our cache turned against us

    While investigating some performance issues, we ran into an ASP.NET Core API that cached a fairly expensive aggregation query for 60 seconds. Under normal load, that was fine: one request rebuilds the cache, everyone else reads from it. Under peak load, dozens of requests would arrive in that same expiry window, all see a cache miss, and all fire the same expensive query in parallel. The database didn't like that. That was the moment when our caching layer stopped helping and started hurting. A burst of requests comes in at the same time, all miss the cache, and all go hammer the database or the downstream API at once. That's a cache stampede . The cache was supposed to protect our backend, and for a few hundred milliseconds it did the opposite. Why this happens IMemoryCache.GetOrCreate (and its async sibling) looks like it protects you, but it doesn't add any locking on its own. Look at the naive version: public async Task<Report> GetReportAsync(string key) ...
    Read more

    A complex system designed from scratch never works

    A few years ago, I worked as an architect on a big mainframe rewrite. I still count it as one of my failures. Not because the technology was wrong, but because I couldn't convince the management team to simplify the approach. Years later, the organization is still struggling to get the new system up and running. I left the project at the time, because I couldn't put my name behind an approach that would take very long and cost a lot of money without a working system to show for it along the way. Gall’s Law That memory keeps coming back to me, because it's a textbook case of Gall's Law playing out in real life. Gall's Law , from John Gall's Systemantics , states it plainly: A complex system that works is invariably found to have evolved from a simple system that worked. A complex system designed from scratch never works, and it cannot be patched to make it work. You have to start over with a simple system that works. What does that mean in practice,...
    Read more