Add comprehensive test coverage for CLI completion functions

[Copilot]

The completion system in pkg/cli/completions.go lacked explicit test coverage for edge cases and special scenarios that could break shell completion behavior.

Changes

Added 8 test functions covering edge cases:

• Special characters in workflow names (dashes, underscores, dots, mixed)
• Invalid/empty .md files and non-.md files in workflow directories
• Case-sensitive prefix matching behavior
• Exact match scenarios
• Long workflow names (200+ characters)
• Engine name consistency across multiple calls
• Case sensitivity in engine name completion

Test structure follows repository conventions:

• Table-driven tests with descriptive subtests
• require.* for setup, assert.* for validations
• 26 subtests across 15 total test functions

Example

func TestCompleteWorkflowNamesWithSpecialCharacters(t *testing.T) {
    tests := []struct {
        name           string
        toComplete     string
        expectedCount  int
        expectContains []string
    }{
        {
            name:           "workflows with test- prefix",
            toComplete:     "test-",
            expectedCount:  2,
            expectContains: []string{"test-workflow", "test-123"},
        },
        // ...
    }
    // ...
}

Ensures shell completions continue working correctly as the codebase evolves.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>[plan] Add test coverage for CLI completion functions</issue_title>
<issue_description>## Objective

Add comprehensive test coverage for shell completion functions in pkg/cli/completions.go to ensure they return correct suggestions and handle edge cases.

Context

The completion system is well-implemented but lacks explicit test coverage. Tests ensure completions continue working correctly as the codebase evolves.

Implementation Approach

1. Create or update test file pkg/cli/completions_test.go

2. Test completion functions:

   func TestCompleteWorkflowNames(t *testing.T) {
       tests := []struct {
           name          string
           setupWorkflows []string
           toComplete    string
           expectContains []string
       }{
           {
               name: "all workflows when empty prefix",
               setupWorkflows: []string{"deploy", "test", "ci"},
               toComplete: "",
               expectContains: []string{"deploy", "test", "ci"},
           },
           {
               name: "filtered workflows with prefix",
               setupWorkflows: []string{"deploy-prod", "deploy-dev", "test"},
               toComplete: "dep",
               expectContains: []string{"deploy-prod", "deploy-dev"},
           },
       }
       // Implementation
   }

3. Test edge cases:

   • Empty workflow directory
   • Invalid workflow files
   • Missing .md extension
   • Special characters in workflow names

4. Test other completion functions:

   • CompleteEngineNames() - Test engine suggestions
   • CompleteDirectories() - Test directory completion
   • MCP server name completion (if testable)

5. Use table-driven tests following gh-aw testing conventions

Files to Create/Modify

• Create/Update: pkg/cli/completions_test.go

  • Add TestCompleteWorkflowNames()
  • Add TestCompleteEngineNames()
  • Add TestCompleteDirectories()
  • Add helper functions for test setup

• Reference: pkg/cli/completions.go

  • Ensure completion functions are testable (accept test directories)

Acceptance Criteria

• Test coverage for CompleteWorkflowNames() includes prefix filtering
• Test coverage for CompleteEngineNames() validates engine list
• Test coverage for CompleteDirectories() validates path handling
• Edge cases tested (empty dir, invalid files, special chars)
• Tests follow table-driven pattern per gh-aw conventions
• Tests pass with make test-unit

References

• Testing conventions: specs/testing.md
• Existing test patterns in pkg/cli/*_test.go
• Cobra completion testing examples
  Related to [plan] Enhance Cobra CLI implementation with completion descriptions and context support #8552

AI generated by Plan Command for discussion #8545

Comments on the Issue (you are @copilot in this section)

• Fixes [plan] Add test coverage for CLI completion functions #8555

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.