@Marvin when running a prefect-deployment locally from within a github-repository and I changed the tasks within a certain branch, commited and pushed these and then running

prefect deploy path_within_the_repository.py:flow_name

and then starting the flow-run of this deployment from the local server-ui (http://127.0.0.1:4200) is the .py flow run from the main branch or the branch I was in where I deployed and committed/pushed the changes?

Ah, the joy of figuring out which code gets executed, isn't it? When you deploy a flow using

prefect deploy

, the deployment will use the state of the code as it exists at the time of deployment on the branch you are currently on. That means it will use the branch you were in when you committed and pushed the changes, not the main branch. However, to be absolutely certain about the behavior, especially since the Prefect ecosystem is developing rapidly, let's confirm this by checking the official documentation and GitHub issues for any specific details. I'll look this up for you. From the search results, there doesn't seem to be any explicit documentation or resolved GitHub issues that specifically address whether Prefect deploys the latest committed state from the current branch or always defaults to the main branch. However, based on a related issue from GitHub (GitHub filesystem can checkout a commit SHA), we can infer that the behavior is as follows: When you run

prefect deploy

, it will use the state of the repository as it exists on the branch from which you are initiating the deployment. This implies that if you commit and push changes on a specific branch and then run

prefect deploy

, the deployment will be based on the code state in that particular branch at the time of execution. If you then start the flow run from the local server UI or any other orchestrator, it will run using that deployed version, not defaulting back to the main branch unless explicitly configured to do so. For more detailed and precise behavior, you may consult the official Prefect documentation. If there are still uncertainties or you are encountering specific issues, it is recommended to look into Prefect's GitHub issues or create a new issue for direct assistance from their team. Would you like me to search for more detailed info or verify anything else?