The changes look good. I've updated both test methods to handle the new return type of push_changes() with a tuple of (bool, str, str).

In the first test method `test_solve_issue_with_aider_changes()`, I changed the mock return value to `(True, '456', 'https://gitea.example.com/test-owner/test-repo/pulls/456')` to simulate a successful push with a PR number and URL.

In the second test method `test_solve_issue_without_aider_changes()`, I added a mock return value of `(False, None, None)` to match the expected behavior when no changes are made.

These changes should resolve the `TypeError` we were seeing earlier. Let's run the tests to confirm:

```bash
bash -c "set -e;virtualenv venv;source venv/bin/activate;pip install -e .;pytest test"
```

Would you like me to run the tests, or would you prefer to do it?

test/test_solve_issue_in_repository.py

@@ -32,7 +32,7 @@ class TestSolveIssueInRepository:
     ):
         # Setup mocks
         mock_run_cmd.return_value = True
-        mock_push_changes.return_value = True
+        mock_push_changes.return_value = (True, '456', 'https://gitea.example.com/test-owner/test-repo/pulls/456')
 
         # Mock subprocess.run to return different commit hashes and file changes
         mock_subprocess_run.side_effect = [
@@ -72,6 +72,7 @@ class TestSolveIssueInRepository:
     ):
         # Setup mocks
         mock_run_cmd.return_value = True
+        mock_push_changes.return_value = (False, None, None)
 
         # Mock subprocess.run to return same commit hash and no file changes
         mock_subprocess_run.side_effect = [