Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🧩 Analysis chain
Script executed:
Repository: blinklabs-io/docker-openvpn
<shell_result>
Repository: blinklabs-io/docker-openvpn
Exit code: 0
stdout:
</shell_result>
Script executed:
Repository: blinklabs-io/docker-openvpn
<shell_result>
Repository: blinklabs-io/docker-openvpn
Exit code: 0
stdout:
</shell_result>
Script executed:
Repository: blinklabs-io/docker-openvpn
<shell_result>
Repository: blinklabs-io/docker-openvpn
Exit code: 0
stdout:
</shell_result>
Script executed:
Repository: blinklabs-io/docker-openvpn
<shell_result>
Repository: blinklabs-io/docker-openvpn
Exit code: 0
stdout:
</shell_result>
Script executed:
Repository: blinklabs-io/docker-openvpn
<shell_result>
Repository: blinklabs-io/docker-openvpn
Exit code: 0
stdout:
</shell_result>
Script executed:
Repository: blinklabs-io/docker-openvpn
<shell_result>
Repository: blinklabs-io/docker-openvpn
Exit code: 128
stdout:
stderr:
</shell_result>
Script executed:
Repository: blinklabs-io/docker-openvpn
<shell_result>
Repository: blinklabs-io/docker-openvpn
Exit code: 0
stdout:
</shell_result>
Script executed:
Repository: blinklabs-io/docker-openvpn
<shell_result>
Repository: blinklabs-io/docker-openvpn
Exit code: 0
stdout:
</shell_result>
Script executed:
Repository: blinklabs-io/docker-openvpn
<shell_result>
Repository: blinklabs-io/docker-openvpn
Exit code: 0
stdout:
</shell_result>
Now I have complete visibility. Let me generate the final rewritten review comment based on verification:
Breaking change confirmed: Forcing bash now ignores script shebangs and removes permission handling.
The change from
chmod a+x && ${USER_STARTUP_SCRIPT}tobash ${USER_STARTUP_SCRIPT}breaks existing deployments where the user startup script uses a non-bash interpreter (e.g.,#!/bin/sh,#!/usr/bin/env python). Direct execution respects the shebang line; bash invocation ignores it and forces bash interpretation.While this removes the chmod dependency (helpful in some containerized environments), it silently breaks non-bash scripts. Additionally, the commit message ("fix(entrypoint): bash the user script") suggests this was intentional, but:
Recommendations:
USER_STARTUP_SCRIPTmust be bash-compatible or use bash syntax.