Відео

why ?

I will do better the next time. If you are looking for the code it is available on the associated blog post: - tgrall.github.io/blog/2021/11/07/how-to-write-a-github-action-annotation-api - github.com/tgrall/check-files-action

Sure, and I still use a lot the standard find and replace, but once you have the possibility to use the natural language is can be very helpful, I am publishing another example today to create data for my product catalog extracting raw data from an Web site and get them as JSON. The idea of these examples is just to think out of the box when using GitHub Copilot.

Do you still have the issue? In which IDE?

Would love to hear your feedback on this. I am using development, quality assurance testing, user acceptance testing and production. Sometimes I will have a temporary penetration testing environment or even accessibility / localisation environments. dev qat, pen, a11y, l10n uat prod I’m also rolling out multiple frontends, backend APIs, serverless lambdas, and infrastructure as code changes (via terraform). dev is automatically updated on the merge of a PR, qat is updated by the testing team via a manual trigger / webhook (click button ins chat channel) pen is used only if we have active penetration testing going on, otherwise it is shut down. And is triggered manually. Same for a11y and l10n. uat is updated by the business analyst / quality assurance team (again via webhook in chat channel) For production when a release is created then the environment will update. We have compliance, linting, building, testing (unit, integration, pact contracts, e2e* and component) We have infrastructure plan / apply with manual approval (prod only) after reviewing the plan. We have updating of assets S3, ECR etc.

First of all , sorry for the late response. You are correct, I am sharing the same "environment" for all developments PR, but it is just a choice of implementation based on your infrastructure. So in my case I have a single K8S cluster, and I use 1 namespace by PR, so this is how I segregate the preview-environment. And what you are describing is probably what I would do it "real life project" (compare with my demo environment used for enablement), as you can see in my demonstration for example I am not talking about infrastructure (beside K8S deployments), and I know that it is missing. You environment and process looks very good and would be nice to learn more about it, if you have blog post or video about this do not hesitate to share it!

Will do better next time

Hello, GitHub Copilot Chat is now generally available, as you can see here: github.blog/2023-12-29-github-copilot-chat-now-generally-available-for-organizations-and-individuals/ It is part of the VS Code, VS and Jetbrains extensions

Hello, GitHub Copilot Chat is now generally available, as you can see here: github.blog/2023-12-29-github-copilot-chat-now-generally-available-for-organizations-and-individuals/

Not long.. as I am working at GitHub, so we have a different process. Be patient, the GitHub Copilot team is working on the waitlist to accept new developers.

Not long.. as I am working at GitHub, so we have a different process. Be patient, the GitHub Copilot team is working on the waitlist to accept new developers.

Hmm you should have received the instruction. Since I am working at GitHub, I am not sure we have the same process. I will look for this information.

You can run some self hosted runners on your machine, but in this video I am using a Kubernetes Cluster that is running on a cloud provider (Google Cloud in the demo). So all the orchestration of the containers (so the runners) is automatically done by Kubernetes.

Hello Jaimerv19 First of all sorry for the late response. I make a very generic IT answer "it depends" :) ... In my demonstration I am using a single K8S cluster and use name spaces to target environment so no "cloud environment". So if we want to target different cloud environment and higher "components" I would probably use "tags" that are generic for all cloud providers. While as you mentioned in GCP you can use projects, and in Azure you can use Ressource Groups. What do you think about using the tags? (like that you can use the same names and concepts on all clouds)

The runners them self are controlled by the Kubernetes cluster, so I am not sure which type of configuration are you looking for? Based on this I will give you more information. PS: Sorry for the late reply.

I have asked Copilot, here the conversation: 😊 Copilot: NantesJUG is a Java User Group in Nantes, France. Me : What is the best programming language? Copilot: The best programming language is Java. Me: What is the best IDE? Copilot: The best IDE is IntelliJ IDEA. Me: What do you think about VS Code? Copilot: I think VS Code is a good IDE. Me: Not better than IntelliJ IDEA? Copilot: I think IntelliJ IDEA is better than VS Code. Me: In which programming language GitHub is written? Copilot: GitHub is written in Ruby. Me: What is the best language to write a compiler? Copilot: The best language to write a compiler is C. Me: What's tgrall favorite programming language? Copilot: tgrall favorite programming language is Java. Me: What's ThatChapThere favorite programming language? Copilot: ThatChapThere favorite programming language is Java.

@@tug-grall My favourite language is Java? Slander! Seriously though I'm pretty sure copilot just picks the language of the file you're in.

Hello Nathan I am inviting you to look at this video, where I deploy in various environment depending of the branch I am working on: ua-cam.com/video/79zVyoxnuWY/v-deo.html Or this documentation page: docs.github.com/en/actions/deployment/deploying-to-your-cloud-provider/deploying-to-azure/deploying-nodejs-to-azure-app-service I am pointing to Azure here, but as you can see on the menu you can use any cloud provider, or any target. Feel free to tell me more about the type of deployment you are doing to see if I need to add more information. Note: the deployment will happen on the "Push" (since the commit is done on the machine of the developer) Tug

@@tug-grall Thanks I will check it out. I am not sure if I am doing it right but I am self hosting and using that to run batch files to do a git pull. Someone told me I am doing it wrong but seems security to me.

You do not need to do a git pull directly you can use a GitHub Action, usually we use this action: - github.com/marketplace/actions/checkout It is totally OK to use self-hosted runner, if you need to access some resources on your network, but you have to manage the process yourself, where GitHub Managed runners are fully managed by GitHub, so you have nothing to do. When using GitHub Hosted Runners, the VM behind it is automatically decommissioned once the job is done, as documented here : docs.github.com/en/actions/using-github-hosted-runners/about-github-hosted-runners#using-a-github-hosted-runner Can you clarify what you mean by "security" in your last comment?

@@tug-grall I am running a git pull on the server from the runner. Right now I do not have an SSH setup to get into the server so by self hosting with very few repos and users I figured this is okay to just have the git pull don from the runner. I am wondering if this is the best option and if it is an okay option.

I will do

Yes, but you need an env variable

You can pass the "name" of an environment as a variable as you are showing. One of the reason to create an environment is to have "secrets" with a fine grained scope or permissions, so in this case you have to create the environment itself using the UI or GitHub API. Do not hesitate to describe more your use case and I will be happy to add information