Fix test coverage gaps: unused imports, mock unix socket init, and cleanup

[Copilot]

• Remove unused patch import from tests/test_func.py
• Fix test_initialize_unix_socket_connection to actually exercise unix-socket initialization
• Add asyncTearDown to tests/test_edge_cases.py for proper cleanup
• Address code review nitpicks (better naming and exception comments)
• Fix tearDown to actually run by removing manual cleanup in tests
• Make db assertion less brittle by accepting numeric values

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

[coderabbitai]

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[Copilot]

Pull request overview

This PR tightens test quality around Redis initialization and cleanup, removing an unused mock import, making the Unix-socket initialization test exercise the real code path, and adding Redis cleanup logic for edge-case tests.

Changes:

• Removed an unused patch import from tests/test_func.py and added MagicMock for more flexible mocking.
• Reworked test_initialize_unix_socket_connection to patch fq.queue.Redis, call FQ._initialize(), and assert that the Unix socket path and DB index are passed correctly.
• Added asyncTearDown and fq_instance tracking in tests/test_edge_cases.py to perform Redis DB flush and connection cleanup around tests that use a real Redis client.

Reviewed changes

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

File	Description
tests/test_func.py	Cleans up mock imports and strengthens the Unix-socket Redis initialization test by exercising the actual _initialize path and verifying constructor kwargs.
tests/test_edge_cases.py	Introduces per-test Redis cleanup via asyncTearDown and tracks real FQ instances to avoid cross-test interference and resource warnings.

---

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

[Copilot]

The new asyncTearDown is intended to flush Redis and close connections after each test, but the current pattern of setting self.fq_instance = None inside tests (e.g., lines 176-185, 189-196, 270-276) means that on successful test runs this teardown block is skipped, so Redis state is not actually cleaned between tests. To ensure the cleanup described in the PR, consider relying on asyncTearDown as the single place that closes and resets fq_instance (and avoid resetting it to None in the tests themselves), or at least avoid clearing self.fq_instance before teardown runs.

[Copilot]

This assertion tightly couples the test to db being the string '0', even though the production code only requires that the logical DB index be 0. To make the test less brittle against harmless implementation changes (e.g., casting db to an int), consider asserting on the numeric value instead, or relaxing the check so it does not depend on the exact type representation.

Suggested change

	self.assertEqual(redis_init_kwargs['db'], '0')
	self.assertEqual(int(redis_init_kwargs['db']), 0)

[ochui]

@copilot apply changes based on the comments in this thread

[Copilot]

@copilot apply changes based on the comments in this thread

I've applied both changes from the review in commit a5c0934:

1. ✅ Fixed tearDown cleanup: Removed manual await fq.close() and self.fq_instance = None from three tests (test_dequeue_payload_none, test_clear_queue_delete_only, test_deep_status_real_redis). Now asyncTearDown properly runs and performs cleanup after each test.

2. ✅ Fixed db assertion brittleness: Changed self.assertEqual(redis_init_kwargs['db'], '0') to self.assertEqual(int(redis_init_kwargs['db']), 0) to accept both string and numeric values, making the test less brittle to implementation changes.

All tests pass including the full edge case test suite (12/12 tests).