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/session_orchestrator_test.go

@@ -8,6 +8,7 @@ import (
 	"testing"
 	"time"
 
+	"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"
 )
@@ -149,6 +150,89 @@ func readOnlyEnv() loop.SessionEnv {
 	return loop.SessionEnv{MemWritable: false}
 }
 
+// fakeHistory records every Append so tests assert the orchestrator persists the
+// user stream and the assistant reply into the chat-history store.
+type fakeHistory struct {
+	mu      sync.Mutex
+	appends []history.Message
+}
+
+func (f *fakeHistory) Append(_ context.Context, msg history.Message) error {
+	f.mu.Lock()
+	f.appends = append(f.appends, msg)
+	f.mu.Unlock()
+	return nil
+}
+
+func (f *fakeHistory) List(context.Context, string, int64, int) ([]history.Message, error) {
+	return nil, nil
+}
+
+func (f *fakeHistory) Recent(context.Context, string, int) ([]history.Message, error) {
+	return nil, nil
+}
+
+func (f *fakeHistory) DeleteSession(context.Context, string) error {
+	return nil
+}
+
+func (f *fakeHistory) NewSubSession(context.Context, string) (string, error) {
+	return "", nil
+}
+
+func (f *fakeHistory) ListSessions(context.Context) ([]history.SessionMeta, error) {
+	return nil, nil
+}
+
+func (f *fakeHistory) records() []history.Message {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	return append([]history.Message(nil), f.appends...)
+}
+
+func TestSubmitPersistsUserAndAssistant(t *testing.T) {
+	t.Parallel()
+	run := newGatedRunner(1)
+	hist := &fakeHistory{}
+	o := NewOrchestrator(OrchestratorOptions{
+		Run:     run.Run,
+		Log:     slog.Default(),
+		History: hist,
+	})
+	run.tickets <- struct{}{}
+	sr, res := o.SubmitSync(context.Background(), "web", []model.Message{userMsg("你好")}, loop.OwnerEnv())
+	if !sr.Accepted || !sr.Immediate {
+		t.Fatalf("submit = %+v, want Accepted+Immediate", sr)
+	}
+	if res == nil {
+		t.Fatal("sync result is nil")
+	}
+	recs := hist.records()
+	if len(recs) != 2 {
+		t.Fatalf("appends = %d, want 2 (user + assistant)", len(recs))
+	}
+	if recs[0].SessionID != "web" || recs[0].Role != history.RoleUser || recs[0].Content != "你好" {
+		t.Fatalf("user record = %+v", recs[0])
+	}
+	if recs[1].SessionID != "web" || recs[1].Role != history.RoleAssistant || recs[1].Content == "" {
+		t.Fatalf("assistant record = %+v", recs[1])
+	}
+}
+
+func TestSubmitDoesNotPersistRejectedTurn(t *testing.T) {
+	t.Parallel()
+	hist := &fakeHistory{}
+	o := NewOrchestrator(OrchestratorOptions{Run: newGatedRunner(0).Run, Log: slog.Default(), History: hist, MaxPending: 1})
+	// Empty turn is rejected before any persistence.
+	sr := o.Submit(context.Background(), "web", nil, loop.OwnerEnv())
+	if sr.Accepted || !sr.Empty {
+		t.Fatalf("empty submit = %+v, want Empty reject", sr)
+	}
+	if n := len(hist.records()); n != 0 {
+		t.Fatalf("appends = %d, want 0 for a rejected turn", n)
+	}
+}
+
 func TestSubmitIdleStartsImmediate(t *testing.T) {
 	t.Parallel()
 	run := newGatedRunner(1)