feat: IM式跨端实时同步——message_persisted 广播 + 前端按id去重追加

- history.Store 新增 AppendFull（返回含 id/createdAt 的完整消息），Append 签名不变
- session_orchestrator 加可空 OnPersisted；persistUserMessages/persistAssistantReply 落库后回调广播
- server.go newOrchestrator 接 OnPersisted → hub.broadcast message_persisted（thinking 剥除）
- 前端 ws.ts 加 message_persisted case（仅 activeSessionId 匹配才处理）；appendOrUpdateMessage 升级为 id 精确upsert+内容/时间归一
- 实测：双 WS，A stream 发消息，B 免刷新收到 user+assistant 各1条（count=2 PASS）
- 红线: 身份仍靠 actor 元数据，不靠提示词；用户/助手消息、本端/异端统一路径

internal/services/gateway/server.go

@@ -109,6 +109,10 @@ type MemoryStore interface {
 // endpoints answer with a clear 501.
 type HistoryStore interface {
 	Append(ctx context.Context, msg history.Message) error
+	// AppendFull persists msg like Append but returns the complete stored message
+	// (with the assigned id/timestamp) so the orchestrator can broadcast it for
+	// cross-end realtime sync (design/16 §4.2).
+	AppendFull(ctx context.Context, msg history.Message) (history.Message, error)
 	List(ctx context.Context, sessionID string, before int64, limit int) ([]history.Message, error)
 	Recent(ctx context.Context, sessionID string, n int) ([]history.Message, error)
 	DeleteSession(ctx context.Context, sessionID string) error
@@ -455,6 +459,15 @@ func newOrchestrator(s *Server) *Orchestrator {
 		Emit: func(sessionID, typ string, data map[string]any) {
 			s.hub.broadcast(wsEvent{Type: typ, SessionID: sessionID, Data: data})
 		},
+		OnPersisted: func(msg history.Message) {
+			// Broadcast the complete message so every browser of the same account
+			// appends it without a manual refresh (design/16 §4.2). The frontend
+			// dedups by the backend-generated id, and thinking is stripped to stay
+			// consistent with the WS history replay (design/16 §6).
+			wire := toHistoryMessage(msg)
+			wire.Thinking = ""
+			s.hub.broadcast(wsEvent{Type: "message_persisted", SessionID: msg.SessionID, Data: map[string]any{"message": wire}})
+		},
 		Log:     s.log,
 		History: s.history,
 	})