Features Released in v1.3.0

• No more running vx init in every repository. Configure your GitHub and OpenAI credentials once and vexal resolves the right config automatically.
• Added -n / --verbatim-notes flag to prepend your own notes to the generated PR body — useful for callouts, deployment steps, or anything the commit history won't capture.
• vexal now checks if your branch exists on remote before attempting to create a PR and provides a clear message if it hasn't been pushed yet.
• Upgraded from GPT-3.5 Turbo to GPT-4o Mini for noticeably better PR generation quality.