taprpc+scripts: detect Podman wrapper and preserve Docker UID mapping

[ffranr]

Detect Podman by checking "$DOCKER --version", allowing overrides via the DOCKER environment variable. Retain --user $UID:$(id -g) for Docker/CI to ensure generated files are user-owned. For Podman, switch to "--user=0:0" to avoid EACCES errors caused by rootless subuid/subgid remapping on bind mounts.

• scripts/gen_sqlc_docker.sh: add runtime user selection; use $DOCKER for run
• taprpc/gen_protos_docker.sh: same detection logic; use $DOCKER for build/run

Fixes "Permission denied" errors with rootless Podman, while maintaining existing Docker behavior.

[gemini-code-assist]

Summary of Changes

Hello @ffranr, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request enhances the gen_sqlc_docker.sh and gen_protos_docker.sh scripts to improve compatibility with both Docker and Podman. By introducing runtime detection and dynamic user mapping, it resolves common 'Permission denied' errors encountered when using rootless Podman, ensuring that generated files maintain correct ownership across different containerization platforms without disrupting existing Docker workflows. This change makes the build and generation processes more robust and adaptable.

Highlights

• Podman Compatibility: The scripts now intelligently detect if Podman is being used as the container runtime, allowing for better compatibility with different container environments.
• Dynamic User Mapping: User ID mapping for container execution is dynamically adjusted; for Docker, it retains the current user's UID/GID, while for Podman, it switches to root (0:0) to prevent permission errors with rootless bind mounts.
• Container Runtime Overrides: The container runtime command can now be overridden using the DOCKER environment variable, providing greater flexibility for users with custom setups.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces logic to detect if podman is being used as a docker wrapper and adjusts the user arguments for docker run commands accordingly. This is a valuable change that fixes permission issues when using rootless Podman. The changes are applied to scripts/gen_sqlc_docker.sh and taprpc/gen_protos_docker.sh. My review focuses on improving the robustness and maintainability of the shell scripts. I've suggested quoting variables to prevent word splitting, extracting duplicated code into a shared helper script to adhere to the DRY principle, and fixing a minor indentation inconsistency to maintain a consistent coding style across the project.

[coveralls]

Pull Request Test Coverage Report for Build 20787517435

Details

• 0 of 0 changed or added relevant lines in 0 files are covered.
• 73 unchanged lines in 18 files lost coverage.
• Overall coverage increased (+0.008%) to 57.01%

---

Files with Coverage Reduction	New Missed Lines	%
asset/group_key.go	2	72.15%
tapdb/mssmt.go	2	90.45%
tapdb/sqlc/transfers.sql.go	2	83.33%
asset/mock.go	3	73.21%
itest/assertions.go	3	87.42%
itest/multisig.go	3	97.94%
rfqmsg/records.go	3	71.05%
tapchannel/aux_leaf_signer.go	3	43.53%
tapdb/interfaces.go	3	80.0%
tapgarden/planter.go	3	80.26%

Totals
Change from base Build 20783469456:	0.008%
Covered Lines:	65567
Relevant Lines:	115010

---

💛 - Coveralls

[ffranr]

/gemini review

[gemini-code-assist]

Code Review

This pull request effectively adds detection for Podman and adjusts the user mapping to prevent permission errors, while maintaining the existing behavior for Docker. The changes are consistently applied across the relevant Makefiles and shell scripts. I've added a couple of suggestions to refactor the Makefile logic to reduce code duplication and improve maintainability. Overall, this is a good improvement.

[ffranr]

/gemini review

[gemini-code-assist]

Code Review

This pull request introduces detection for Podman and adjusts Docker command user arguments to resolve permission issues with rootless Podman, while maintaining existing behavior for Docker. The changes are well-structured, centralizing the detection logic in a new helper script and updating Makefiles and build scripts to use it. This is a good improvement for developer environment flexibility. I've added a few minor suggestions to quote the DOCKER variable in the shell scripts to improve their robustness.

[ffranr]

/gemini review

[gemini-code-assist]

Code Review

This pull request introduces detection for Podman to adjust user arguments, resolving permission errors with rootless setups while maintaining compatibility with Docker. The changes are well-implemented, centralizing detection logic in a new scripts/docker_helpers.sh script for shell files and using Makefile variables for make targets. This is a clean solution to the problem. My review includes a couple of suggestions to improve the robustness of the shell scripts by properly quoting variables.

[jtobin]

LGTM. I used to do my own local munging of this stuff for podman use, but then eventually grudgingly adopted Docker. Maybe I should retvrn to podman now?

[darioAnongba]

Podman for the win.