feat(set): add --stdin flag for multiline environment variables

[jdx]

Summary

• Adds --stdin flag to mise set that reads the value from stdin until EOF, enabling multiline environment variables (e.g., SSH keys, certificates)
• Strips a single trailing newline to match gh secret set behavior (echo "val" | mise set --stdin KEY stores "val")
• Validates exactly one key is provided without KEY=VALUE syntax

Closes #6878

Test plan

• printf 'line1\nline2' | mise set --stdin MULTI_LINE stores multiline value correctly
• printf 'hello\n' | mise set --stdin TRAILING_NL strips trailing newline
• mise set --stdin KEY1 KEY2 fails with error
• mise set --stdin KEY1=value fails with error
• E2E tests pass: mise run test:e2e test_set

🤖 Generated with Claude Code

---

Note

Low Risk
Low risk: adds an opt-in --stdin path to mise set plus validations; existing set/get/prompt behavior is unchanged unless the new flag is used.

Overview
Adds mise set --stdin to read an env var value from stdin until EOF, enabling multiline values, and strips a single trailing newline for parity with gh secret set.

Enforces --stdin usage rules (exactly one key, no KEY=VALUE syntax, and conflicts with --prompt), and updates CLI docs/man page/completions plus e2e coverage for multiline input and error cases.

^{Written by Cursor Bugbot for commit 2a27930. This will update automatically on new commits. Configure here.}

[gemini-code-assist]

Summary of Changes

Hello @jdx, 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 significantly enhances the mise set command by introducing a --stdin flag. This feature allows users to set environment variables with values piped from standard input, which is particularly beneficial for handling multiline strings or sensitive data without exposing it directly on the command line. The implementation includes robust input validation and careful handling of newlines to ensure consistent and expected behavior.

Highlights

• New --stdin flag for mise set: Introduced a --stdin flag to the mise set command, allowing environment variable values to be read directly from standard input until EOF. This enables setting multiline environment variables, which is useful for things like SSH keys or certificates.
• Trailing newline stripping: The --stdin flag automatically strips a single trailing newline character from the input, matching the behavior of tools like gh secret set.
• Input validation for --stdin: Added validation to ensure that when --stdin is used, exactly one key is provided and that it does not use the KEY=VALUE syntax, as the value is expected from stdin.
• Updated documentation and tests: The command's help text has been updated to include examples for --stdin, and comprehensive end-to-end tests have been added to verify its functionality and error handling.

Changelog

• e2e/cli/test_set
  • Added new end-to-end tests for the --stdin flag, verifying multiline value storage, trailing newline stripping, and correct error handling for invalid input.
• src/cli/set.rs
  • Imported std::io::Read for reading from standard input.
  • Added the --stdin flag to the Set struct with appropriate clap attributes, including conflicts_with for the prompt flag.
  • Modified the run method to incorporate logic for reading environment variable values from stdin when the --stdin flag is present.
  • Implemented validation checks to ensure --stdin is used with a single key and without KEY=VALUE syntax.
  • Added logic to strip a single trailing newline from the stdin input.
  • Updated the AFTER_LONG_HELP documentation string to include examples for using the new --stdin flag.

Activity

• The author has provided a detailed summary of the changes and a comprehensive test plan, including specific test cases for multiline values, trailing newlines, and validation failures.
• All listed E2E tests are marked as passing, indicating thorough testing of the new functionality.
• The PR description notes that it was generated with Claude Code, suggesting an AI-assisted development process.

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. ↩

[Copilot]

Pull request overview

Adds a --stdin flag to mise set to support setting multiline environment variable values by reading from stdin, including trimming a single trailing newline and validating correct usage.

Changes:

• Added --stdin CLI flag and implementation for reading value from stdin until EOF.
• Prevented --stdin from triggering “get” behavior and added usage validation/error paths.
• Added E2E coverage for multiline input, trailing newline stripping, and invalid invocations.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.

File	Description
src/cli/set.rs	Implements --stdin flag behavior, validation, and help text examples
e2e/cli/test_set	Adds E2E tests for multiline stdin input, trailing newline stripping, and failure cases

---

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

[Copilot]

The help text claims “binary-safe input”, but the implementation reads into a String (UTF-8), which is not binary-safe and will fail on non-UTF-8 bytes. Either adjust the wording to match reality (e.g., “multiline / UTF-8 text input”) or change the implementation to read raw bytes and explicitly handle UTF-8 decoding/validation (and document what happens on invalid UTF-8).

Suggested change

	/// Read the value from stdin (for multiline or binary-safe input)
	///
	/// When using --stdin, provide a single key without a value.
	/// The value will be read from stdin until EOF.
	/// Read the value from stdin (for multiline / UTF-8 text input)
	///
	/// When using --stdin, provide a single key without a value.
	/// The value will be read from stdin until EOF and must be valid UTF-8.

[Copilot]

read_to_string requires valid UTF-8; if stdin contains non-UTF-8 bytes, this will error even though the flag help suggests binary-safe behavior. If binary input is truly a requirement, read into a Vec<u8> and then decide on a supported encoding/representation (or explicitly error with a clearer message that stdin must be UTF-8).

Suggested change

	let mut value = String::new();
	std::io::stdin().read_to_string(&mut value)?;
	let mut buf = Vec::new();
	std::io::stdin().read_to_end(&mut buf)?;
	let mut value = String::from_utf8(buf)
	.map_err(|e| anyhow::anyhow!("stdin must be valid UTF-8: {}", e))?;

[Copilot]

The error message would be more actionable if it included the expected invocation format. Consider something like: "--stdin expects exactly one KEY (no KEY=VALUE). Usage: mise set --stdin KEY".

Suggested change

	bail!("--stdin requires exactly one environment variable key");
	bail!("--stdin expects exactly one KEY (no KEY=VALUE). Usage: mise set --stdin KEY");

[gemini-code-assist]

Code Review

This pull request introduces a --stdin flag to mise set, allowing for multiline environment variables to be set from standard input. The changes include adding the new flag, implementing the logic to read from stdin, and stripping a single trailing newline to align with gh secret set's behavior. The implementation is well-tested with new e2e tests covering multiline values, newline stripping, and error cases. The feedback provided focuses on improving the readability of the newline stripping logic.

[gemini-code-assist]

The logic for stripping the trailing newline is correct, but it could be made more explicit and readable. Using truncate with ends_with for both \r\n and \n makes the intent clearer and is just as efficient.

I'd suggest replacing this block with:

if value.ends_with("\r\n") {
    value.truncate(value.len() - 2);
} else if value.ends_with('\n') {
    value.truncate(value.len() - 1);
}

if value.ends_with("\r\n") {
    value.truncate(value.len() - 2);
} else if value.ends_with('\n') {
    value.truncate(value.len() - 1);
}

[jdx]

bugbot run

[cursor]

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{Bugbot Autofix is ON, but a Cloud Agent failed to start.}

[github-actions]

Hyperfine Performance

mise x -- echo

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
mise-2026.2.9 x -- echo	23.3 ± 0.5	22.2	28.9	1.00
mise x -- echo	24.2 ± 0.5	22.9	30.1	1.04 ± 0.03

mise env

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
mise-2026.2.9 env	22.8 ± 0.5	21.8	26.2	1.00
mise env	23.5 ± 0.6	22.5	33.2	1.03 ± 0.04

mise hook-env

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
mise-2026.2.9 hook-env	23.5 ± 0.4	22.5	25.9	1.00
mise hook-env	24.5 ± 0.5	23.1	27.6	1.04 ± 0.03

mise ls

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
mise-2026.2.9 ls	21.6 ± 0.5	20.5	28.0	1.00
mise ls	22.6 ± 0.5	21.4	25.0	1.04 ± 0.03

xtasks/test/perf

Command	mise-2026.2.9	mise	Variance
install (cached)	123ms	124ms	+0%
ls (cached)	76ms	76ms	+0%
bin-paths (cached)	81ms	81ms	+0%
task-ls (cached)	556ms	557ms	+0%