7 Commits

Author	SHA1	Message	Date
john	e42417bd6e	feat(wechat): add subscribe morning reminder, plaza welcome, and LLM fallback ... Enable daily morning greeting on reply 1 (with custom time, modify, and cancel), random greeting delivery, M发现 in subscribe welcome, and optional LLM parsing when rules miss. Also fix WeChat MP draft/config error passthrough and add Tang E2E scripts. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-09-10 17:32:10 +08:00
john	212ff3ff80	Add User Model Service and Temporal Recall for MeMind V0.1. ... Introduce UMS ingest/snapshot pipeline, Context Planner with multi-source recall, runtime context injection, canonical user mapping, and session snapshot loading on auth/me. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-09-03 23:25:18 +08:00
john	5de58af9ed	fix(wechat): resolve scheduled task cancel via manage LLM instead of hard rules ... Use a lightweight LLM over active task lists to pick taskId for cancel, exclude page.generate from scheduled-task inbound, and remove single-task auto-cancel so Cursor page generation stays isolated. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-08-29 13:45:28 +08:00
john	ad6dcc283f	feat(cursor): wire executor through portal, admin, and wechat routes ... Register cursor in LLM executor bindings, route page/code tasks through cursor runtime selection, and bootstrap wechat cursor policy services. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-08-27 09:33:47 +08:00
john	91e140d402	feat(wechat): add admin-pluggable LLM intent router separate from H5. ... 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>	2026-08-01 20:57:41 +08:00
john	d87bfde501	merge: server architecture modularization	2026-07-24 19:18:14 +08:00
john	785731d98d	refactor: modularize portal server and harden session recovery	2026-07-24 19:10:44 +08:00