7 Commits

Include renames

Author	SHA1	Message	Date
chenmingxuan	3dd96078db	feat: add cache routing alignment and usage visibility for 2.5.0	2026-11-02 17:15:59 +08:00
chenmingxuan	2328a4df0c	fix: improve cross-device evidence and exploration lifecycle ... Align Responses cache affinity across execution and summary calls, preserve required checks and evidence uncertainty, and allow safe deletion of inactive explorations while retaining independent reruns. Validation: backend suite passed except intentional prompt golden drift, then all 17 transcript tests passed after snapshot refresh; 268 frontend tests and production build passed; Ruff, quality ratchet and core type checks passed.	2026-10-17 19:43:20 +08:00
chenmingxuan	a66803651a	fix: improve cross-device evidence, request diagnostics and prompt efficiency	2026-10-17 14:55:45 +08:00
chenmingxuan	c818a09a49	fix: align Responses messages and video exports	2026-09-29 00:12:35 +08:00
chenmingxuan	2ec563c079	fix: support max reasoning and custom model selection for 1.0.0	2026-09-23 00:24:35 +08:00
chenmingxuan	7b1a0755e2	feat: enable full AI automation and safe startup updates	2026-09-22 23:50:03 +08:00
chenmingxuan	2ddec53954	feat: add Chinese UI, Responses models, and mirrored Windows setup ... Localize the web console and persist custom model and capability settings. Use OpenAI Responses exclusively and move runtime limits into environment configuration. Bootstrap uv and the virtual environment on Windows, support optional China mirrors, and package source distributions without environments, build output, or credentials. Update regression tests and repository quality checks for the new behavior.	2026-09-22 19:16:17 +08:00