[go-migration] Update troubleshooting guide

[kiril-keranov]

Updating the troubleshooting guide for the integration tests of the go-based java buildpack with regard to a couple of docker issues that might occur in local setup runs.

[Copilot]

Pull request overview

This PR updates the troubleshooting section of the integration test README to document two Docker-related issues that can occur during local setup runs and their solutions.

Changes:

• Added troubleshooting guidance for "no route to host" errors during staging
• Added troubleshooting guidance for container removal permission denied errors during test teardown

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

This is a very long run-on sentence (217 words). Consider breaking it into multiple sentences or a bulleted list for better readability. For example, separate the diagnostic steps from the mitigation steps.

Suggested change

Check if the url, for which the issue appears, is accessible from the host machine. If the url appears reachable and can be accessed successfully, check again from within the corresponding switchblade container where the test is run. This can be achieved with `docker exec -it <container_id> /bin/bash` while the container is still up in order to ssh to it and further try for example to issue a `curl` to the url. If the `connect: no route to host` can be reproduced from within the corresponding switchblade container, you can try the following in order to mitigate it:

Check whether the URL that is failing is accessible from the host machine. If the URL is reachable from the host, check it again from within the corresponding Switchblade container where the test is run. You can open a shell in the container with `docker exec -it <container_id> /bin/bash` while the container is still running. From there, try issuing a `curl` request to the URL. If the `connect: no route to host` error can be reproduced from within the corresponding Switchblade container, you can try the following in order to mitigate it:

[Copilot]

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated 4 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

This paragraph is very long and difficult to read. Consider breaking it into multiple sentences or bullet points to improve readability and make the troubleshooting steps clearer.

Suggested change

	Check if the url, for which the issue appears, is accessible from the host machine. If the url appears reachable and can be accessed successfully, check again from within the corresponding switchblade container where the test is run. This can be achieved with `docker exec -it <container_id> /bin/bash` while the container is still up in order to access the container interactively and, for example, issue a `curl` to the url from within it. If the `connect: no route to host` can be reproduced from within the corresponding switchblade container, you can try the following in order to mitigate it:
	1. Execute `docker network prune` - this will remove any unused networks including `switchblade-internal` bridge networks set while running the integration tests.
	2. Execute `sudo systemctl restart docker` - restarting docker.
	To troubleshoot this issue:
	1. Check if the URL for which the issue appears is accessible from the host machine.
	2. If the URL is reachable from the host, check it again from within the corresponding Switchblade container where the test is run. You can do this with `docker exec -it <container_id> /bin/bash` while the container is still running, and then issue a `curl` to the URL from inside the container.
	3. If the `connect: no route to host` error can be reproduced from within the corresponding Switchblade container, you can try the following in order to mitigate it:
	1. Execute `docker network prune` - this will remove any unused networks including `switchblade-internal` bridge networks set while running the integration tests.
	2. Execute `sudo systemctl restart docker` - restarting docker.