fix(task): prevent wildcard glob test:* from matching parent task test

[jdx]

Summary

• When a task named test has run = [{ task = "test:*" }], the * wildcard incorrectly matched the task itself (because * matched the empty string for the task part after splitting on :), causing a circular dependency error
• Fixed get_matching() to require that task:* patterns only match tasks that actually have a colon-separated suffix (e.g. test:foo, test:bar), not the parent task test
• Added unit test and e2e test

Fixes #8138

Test plan

• Unit test test_get_matching_wildcard_does_not_match_parent verifies the pattern matching logic
• E2e test test_task_wildcard_no_self_match verifies the full flow with mise run test

🤖 Generated with Claude Code

---

Note

Low Risk
Small, targeted change to task-glob matching semantics plus additional tests; low risk aside from potentially impacting edge-case wildcard behavior.

Overview
Fixes GetMatchingExt::get_matching so patterns with an explicit : task glob (e.g. test:*) only match tasks that actually have a colon-separated suffix, preventing the parent task test from being selected and creating circular dependencies.

Adds a focused unit test for the matching behavior and a new e2e task test ensuring mise run test runs test:foo/test:bar without invoking itself.

^{Written by Cursor Bugbot for commit cfbeeeb. 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 addresses a critical bug where wildcard task patterns, such as test:*, would inadvertently match their parent task (test), leading to circular dependencies and execution failures. The core change modifies the task matching logic to ensure that wildcard patterns only apply to tasks with a specific suffix, thereby preventing self-matching and ensuring correct task delegation.

Highlights

• Prevented circular dependency in task execution: The test:* wildcard pattern no longer incorrectly matches the parent test task, resolving a circular dependency issue.
• Refined get_matching() logic: The get_matching() function now requires task:* patterns to match tasks with a colon-separated suffix, excluding the parent task itself.
• Added comprehensive testing: New unit and end-to-end tests were introduced to validate the corrected wildcard matching behavior.

Changelog

• e2e/tasks/test_task_wildcard_no_self_match
  • Added a new e2e test to confirm that test:* does not match test.
• src/task/mod.rs
  • Modified get_matching function to prevent * from matching empty key_task or stripped_task when a wildcard is used.
  • Added a unit test test_get_matching_wildcard_does_not_match_parent to verify the new matching logic.

Activity

• A unit test test_get_matching_wildcard_does_not_match_parent was added to verify the pattern matching logic.
• An e2e test test_task_wildcard_no_self_match was added to verify the full flow with mise run test.
• The pull request was generated with Claude Code.

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. ↩

[cursor]

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

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

[gemini-code-assist]

Code Review

This pull request correctly fixes a bug where a wildcard task dependency could match its parent task, causing a circular dependency. The fix is straightforward and effective, preventing the wildcard from matching an empty task suffix. The addition of both a unit test and an end-to-end test ensures the fix is well-covered. The changes are solid, and I have one minor suggestion to make the new unit test more concise.

[gemini-code-assist]

For improved clarity and robustness, you could consolidate these assertions into a single assert_eq! that checks the exact contents and order of the matched tasks. This makes the test more concise and ensures no other unexpected tasks are matched.

Since BTreeMap iterates over keys in sorted order, the order of matches is deterministic.

Suggested change

	assert_eq!(matches.len(), 2);
	assert!(matches.contains(&&"test:foo".to_string()));
	assert!(matches.contains(&&"test:bar".to_string()));
	assert!(!matches.contains(&&"test".to_string()));
	assert_eq!(
	matches,
	vec![&"test:bar".to_string(), &"test:foo".to_string()]
	);

[Copilot]

Pull request overview

This PR fixes a bug where wildcard glob patterns like test:* incorrectly matched parent tasks without suffixes (e.g., test), causing circular dependency errors. The fix ensures that * wildcards only match tasks with actual colon-separated suffixes.

Changes:

• Modified pattern matching logic to require non-empty task parts when using * wildcards
• Added unit test to verify the corrected pattern matching behavior
• Added e2e test to validate the fix in a real-world scenario

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File	Description
src/task/mod.rs	Updated wildcard matching logic to prevent self-matches and added unit test
e2e/tasks/test_task_wildcard_no_self_match	Added e2e test verifying wildcard patterns don't match parent tasks

---

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

[github-actions]

Hyperfine Performance

mise x -- echo

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
mise-2026.2.13 x -- echo	24.1 ± 0.5	23.3	29.5	1.00
mise x -- echo	24.1 ± 0.5	23.3	29.4	1.00 ± 0.03

mise env

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
mise-2026.2.13 env	23.8 ± 0.8	22.9	31.3	1.01 ± 0.04
mise env	23.6 ± 0.3	23.0	25.4	1.00

mise hook-env

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
mise-2026.2.13 hook-env	24.2 ± 0.5	23.4	26.2	1.00
mise hook-env	24.4 ± 0.4	23.7	26.3	1.01 ± 0.03

mise ls

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
mise-2026.2.13 ls	22.6 ± 0.7	21.8	31.4	1.00
mise ls	22.9 ± 0.5	22.1	27.2	1.01 ± 0.04

xtasks/test/perf

Command	mise-2026.2.13	mise	Variance
install (cached)	128ms	127ms	+0%
ls (cached)	80ms	79ms	+1%
bin-paths (cached)	84ms	83ms	+1%
task-ls (cached)	812ms	821ms	-1%