v0.2.0

New Features

• Codex model support: Models like gpt-5.1-codex now work via the /responses API endpoint
• Faster GPT-5.x: Automatically uses reasoning_effort: "none" for gpt-5/gpt-5.1/gpt-5.2, reducing response time while still maintaining quality

Improvements

• Default model: Changed from gpt-5-mini to gpt-4.1 - faster and with same-ish quality among free models
• Prose commit bodies: -d and -a modes now generate small paragraphs to provide context instead of bullet lists
• Better error messages: HTTP 400 errors now point to GitHub Copilot settings page

Full Changelog: v0.1.0...v0.2.0

v0.1.0

Full Changelog: https://github.com/prankstr/ghcc/commits/v0.1.0