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
parent cdc265d7e0
commit 91e140d402
14 changed files with 1145 additions and 4 deletions
@@ -168,6 +168,16 @@ H5_PUBLIC_BASE_URL=http://127.0.0.1:5173
 # MEMIND_CHAT_ROUTER_MODEL_PROVIDER_KEY_ID=<h5_llm_provider_keys.id>
 # MEMIND_CHAT_ROUTER_MODEL=deepseek-v4-pro

+# 微信服务号专用 LLM 意图层（独立于 H5 chatIntentRouter；memindadm 可插拔）
+# 默认关闭；Shadow=1 时只记日志不改行为；canary 留空=全员
+# MEMIND_WECHAT_INTENT_LLM_ENABLED=0
+# MEMIND_WECHAT_INTENT_LLM_SHADOW=1
+# MEMIND_WECHAT_INTENT_MODEL_PROVIDER_KEY_ID=
+# MEMIND_WECHAT_INTENT_MODEL=
+# MEMIND_WECHAT_INTENT_MIN_CONFIDENCE=0.65
+# MEMIND_WECHAT_INTENT_TIMEOUT_MS=4000
+# MEMIND_WECHAT_INTENT_CANARY_OPENIDS=
+
 # H5 Session stream replay（docs/h5-session-architecture-20260706.md Patch 4c）
 # 默认 0：session SSE 仍纯透传 goosed；设 1 时 Portal 持久化 session 事件并支持 Last-Event-ID 重连补发。
 # MEMIND_SESSION_STREAM_REPLAY=0