{"version":"0.27.4","date":"2025-11-28","dateFormatted":"November 28, 2025","url":"https://docs.factory.ai/changelog/release-notes#v0.27.4","jsonUrl":"https://docs.factory.ai/changelog/releases/0.27.4.json","summary":"Interleaved thinking support, show thinking setting, and hooks permanently enabled","surfaces":["cli"],"changes":[{"type":"feature","surface":"cli","title":"Interleaved thinking support"},{"type":"feature","surface":"cli","title":"Show thinking setting"},{"type":"feature","surface":"cli","title":"Hooks always enabled"},{"type":"fix","surface":"cli","title":"Fixed ESC/Q navigation in `/model` menus - pressing ESC or Q now properly navigates back to previous menu level instead of closing all menus"},{"type":"fix","surface":"cli","title":"Fixed garbage characters appearing in prompt input caused by terminal response bytes leaking into stdin"},{"type":"fix","surface":"cli","title":"Fixed reasoning effort display in spec mode to correctly reflect the actual reasoning effort being used"},{"type":"fix","surface":"cli","title":"Fixed OpenAI chat completions streaming for tool calls"},{"type":"fix","surface":"cli","title":"Improved Gemini's usage of the todo tool with better prompting"},{"type":"fix","surface":"cli","title":"Fixed model warmup for GLM-4.6"},{"type":"fix","surface":"cli","title":"Fixed `/install-github-app` command issues"}],"security":[],"deprecations":[],"contentText":"New features\n\n- Interleaved thinking support - Display multiple thinking blocks during streaming, including redacted thinking blocks with safety messages\n- Show thinking setting - Show AI thinking/reasoning on the main view, turn on/off in /settings\n- Hooks always enabled - The hooks feature is now permanently enabled and available via the /hooks command\n\nBug fixes\n\n- Fixed ESC/Q navigation in /model menus - pressing ESC or Q now properly navigates back to previous menu level instead of closing all menus\n- Fixed garbage characters appearing in prompt input caused by terminal response bytes leaking into stdin\n- Fixed reasoning effort display in spec mode to correctly reflect the actual reasoning effort being used\n- Fixed OpenAI chat completions streaming for tool calls\n- Improved Gemini's usage of the todo tool with better prompting\n- Fixed model warmup for GLM-4.6\n- Fixed /install-github-app command issues"}