feat(history): 会话消息持久化 + 主/次级会话（design/16）

- runtime/history: Store + HistoryStore 接口（Append/List 游标分页/Recent/DeleteSession/NewSubSession/ListSessions），主会话固定 web、次级 web:<uuid>
- db 迁移 0003: chat_sessions + chat_messages + idx_chat_msgs_session_created（事务幂等）
- gateway: GET/POST /sessions、GET /sessions/{id}/messages 热分页、DELETE /sessions/{id}（主不可删 403）；Deps.History 可空注入
- 编排层落库: session_persist.go（submitInternal 写用户消息、completeTurn 写助手消息，拒绝的消息不落库）
- WS: wsEvent 加 sessionId 定向 + history 回放帧（握手上行后回放主会话最新 50 条，thinking 剥离）
- wire.go 装配 History 到 gateway.Deps.History
- 端到端实测: POST /sessions 建次级 201 / GET /sessions 列表 / POST /chat 后 /messages 读到 user+assistant / DELETE 次级成功 / DELETE 主会话 403

internal/services/gateway/ws_hub.go

@@ -17,6 +17,7 @@ import (
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/auth"
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/bus"
 	apperr "git.yeij.top/AskaEth/Cyrene_v2/internal/errors"
+	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/history"
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/loop"
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/model"
 )
@@ -41,10 +42,11 @@ const (
 // used by the streaming path so a client can correlate a burst of streamed
 // events to one assistant turn and keep them in order.
 type wsEvent struct {
-	Type   string `json:"type"`
-	TurnID string `json:"turnId,omitempty"`
-	Seq    int    `json:"seq,omitempty"`
-	Data   any    `json:"data,omitempty"`
+	Type      string `json:"type"`
+	TurnID    string `json:"turnId,omitempty"`
+	Seq       int    `json:"seq,omitempty"`
+	SessionID string `json:"sessionId,omitempty"`
+	Data      any    `json:"data,omitempty"`
 }
 
 // wsInbound is the client→server frame. Data carries the per-type payload.
@@ -68,15 +70,16 @@ type wsConn struct {
 
 // hub owns the connection set and relays bus events to every client.
 type hub struct {
-	mu          sync.RWMutex
-	conns       map[*wsConn]struct{}
-	bus         bus.Bus
-	runner      Chatter
-	auditor     SubagentAuditor
-	taskOutputs TaskOutputStore
+	mu           sync.RWMutex
+	conns        map[*wsConn]struct{}
+	bus          bus.Bus
+	runner       Chatter
+	auditor      SubagentAuditor
+	taskOutputs  TaskOutputStore
 	voice        VoiceService
 	streaming    bool
 	orchestrator *Orchestrator
+	history      HistoryStore
 	log          *slog.Logger
 	upgrader     websocket.Upgrader
 	origins      map[string]bool
@@ -96,6 +99,7 @@ func newHub(s *Server) *hub {
 		taskOutputs: s.taskOutputs,
 		voice:       s.voice,
 		streaming:   s.streaming,
+		history:     s.history,
 		log:         s.log,
 		origins:     origins,
 		allowAll:    allowAll,
@@ -222,7 +226,7 @@ func (h *hub) streamChat(ctx context.Context, payload any) {
 		_ = json.Unmarshal(b, &req)
 	}
 	if h.runner == nil || (strings.TrimSpace(req.Text) == "" && strings.TrimSpace(req.Image) == "") {
-		h.broadcast(wsEvent{Type: "stream_end", TurnID: newTurnID(), Seq: int(h.streamSeq.Add(1)), Data: map[string]any{"stopReason": "idle"}})
+		h.broadcast(wsEvent{Type: "stream_end", TurnID: newTurnID(), Seq: int(h.streamSeq.Add(1)), SessionID: req.SessionID, Data: map[string]any{"stopReason": "idle"}})
 		return
 	}
 	if req.SessionID == "" {
@@ -248,19 +252,19 @@ func (h *hub) streamChat(ctx context.Context, payload any) {
 func (h *hub) runTurn(ctx context.Context, sessionID string, msgs []model.Message, env loop.SessionEnv) (*loop.Result, error) {
 	turnID := newTurnID()
 	if h.runner == nil || len(msgs) == 0 {
-		h.broadcast(wsEvent{Type: "stream_end", TurnID: turnID, Seq: int(h.streamSeq.Add(1)), Data: map[string]any{"stopReason": "idle"}})
+		h.broadcast(wsEvent{Type: "stream_end", TurnID: turnID, Seq: int(h.streamSeq.Add(1)), SessionID: sessionID, Data: map[string]any{"stopReason": "idle"}})
 		return &loop.Result{StopReason: "idle"}, nil
 	}
 	res, err := h.runner.Run(loop.WithSessionEnv(ctx, env), sessionID, msgs)
 	if err != nil {
 		h.log.Error("chat run", "err", err, "session", sessionID)
-		h.broadcast(wsEvent{Type: "stream_end", TurnID: turnID, Seq: int(h.streamSeq.Add(1)), Data: map[string]any{"stopReason": "error", "error": err.Error()}})
+		h.broadcast(wsEvent{Type: "stream_end", TurnID: turnID, Seq: int(h.streamSeq.Add(1)), SessionID: sessionID, Data: map[string]any{"stopReason": "error", "error": err.Error()}})
 		return nil, err
 	}
 	if !h.streaming {
-		h.broadcast(wsEvent{Type: "stream_chunk", TurnID: turnID, Seq: int(h.streamSeq.Add(1)), Data: map[string]any{"delta": res.Text}})
+		h.broadcast(wsEvent{Type: "stream_chunk", TurnID: turnID, Seq: int(h.streamSeq.Add(1)), SessionID: sessionID, Data: map[string]any{"delta": res.Text}})
 	}
-	h.broadcast(wsEvent{Type: "stream_end", TurnID: turnID, Seq: int(h.streamSeq.Add(1)), Data: map[string]any{"stopReason": res.StopReason, "steps": res.Steps}})
+	h.broadcast(wsEvent{Type: "stream_end", TurnID: turnID, Seq: int(h.streamSeq.Add(1)), SessionID: sessionID, Data: map[string]any{"stopReason": res.StopReason, "steps": res.Steps}})
 	return res, nil
 }
 
@@ -330,6 +334,7 @@ func (s *Server) handleWS(w http.ResponseWriter, r *http.Request) {
 		claims: claims,
 	}
 	s.hub.register(c)
+	s.hub.replayHistory(c, history.MainSessionID)
 	go c.writePump()
 	go c.readPump()
 }