Add keyword fallback and dedupe for pgvector resolve, score personal vs episodic memories by relevance, record WeChat recall product events, and disable broken chatrecall on Postgres session storage.
Co-authored-by: Cursor <cursoragent@cursor.com>
Schedule LLM now binds an explicit provider key and fails closed on network errors so dead relay endpoints cannot block ordinary chat; relay bootstrap is opt-in only.
Co-authored-by: Cursor <cursoragent@cursor.com>
Give WeChat MP its own chat.general→page.generate LLM refinement layer with memindadm toggles, shadow mode, and canary openids so service account routing stays independent of the H5 chatIntentRouter.
Co-authored-by: Cursor <cursoragent@cursor.com>
Persist goal runs in MySQL, bind agent runs to checkpoints, expose awaiting-approval
UX in chat, and add admin inspection routes with local verify scripts.
Co-authored-by: Cursor <cursoragent@cursor.com>
Finalize page delivery contracts after worker execution, fetch session messages via tkmindProxy, and append public page URLs to WeChat notifications.
Co-authored-by: Cursor <cursoragent@cursor.com>
Introduce scheduled-task-automation for H5 and WeChat, persist tasks in h5_scheduled_tasks, and run due jobs via a dedicated worker that executes agent tasks and delivers results.
Co-authored-by: Cursor <cursoragent@cursor.com>
Publication routes and share shells were missing the Rybbit tracker, and
bootstrap now reuses the stored MindSpace analytics secret when Rybbit env
secret is absent.
Co-authored-by: Cursor <cursoragent@cursor.com>
john