feat: IM平台列 + deviceID标识 + 会话持久化完善

- agent-96: chat_messages 加 platform 列(迁移0004) + IM主人私聊落主会话web(带platform) + 前端按平台过滤契约 + message_persisted 带 platform(复用 BroadcastPersisted)
- agent-97: chat_messages 加 device_id 列(迁移0005) + history.Message.DeviceID + Web发消息带deviceId(localStorage getClientId) + IM persistToMain 带 deviceID + 前端气泡展示 SourceLabel + 修主会话基础2个bug(fn scanMessage语法/DDL缺列)
- design/16 §4.4(平台) + §4.5(deviceID) 已入档
- 实机: POST /chat 带 deviceId 读回 user/assistant 均带 deviceId+platform; 后端 build/vet/test 绿 + 前端 build 绿
- 红线: 身份靠 actor 元数据; 禁止 shell 读 .env(JWT冒烟由主会话跑)

internal/db/migrations/0004_chat_history_platform.down.sql

@@ -0,0 +1,25 @@
+-- 0004_chat_history_platform: rolls back the platform column added by the up
+-- migration. SQLite's ALTER DROP COLUMN is version-dependent (3.35+), so the column
+-- is removed by recreating the table without it — universally safe and lossless
+-- (the platform tag is not needed once the column is gone).
+
+CREATE TABLE chat_messages_new (
+    id         TEXT PRIMARY KEY,
+    session_id TEXT NOT NULL,
+    role       TEXT NOT NULL,
+    content    TEXT NOT NULL,
+    mode       TEXT,
+    mood       TEXT,
+    image      TEXT,
+    thinking   TEXT,
+    created_at INTEGER NOT NULL
+);
+
+INSERT INTO chat_messages_new (id, session_id, role, content, mode, mood, image, thinking, created_at)
+    SELECT id, session_id, role, content, mode, mood, image, thinking, created_at FROM chat_messages;
+
+DROP TABLE chat_messages;
+ALTER TABLE chat_messages_new RENAME TO chat_messages;
+
+CREATE INDEX IF NOT EXISTS idx_chat_msgs_session_created
+    ON chat_messages (session_id, created_at DESC);

internal/db/migrations/0004_chat_history_platform.up.sql

@@ -0,0 +1,13 @@
+-- 0004_chat_history_platform: tag every chat message with its source platform
+-- (DevDocs/design/16 §4.4). The Web main session is shared across platforms: the
+-- Web client renders the full session, while each IM adapter filters to its own
+-- platform lane. Messages that originate on the Web carry 'web'; IM owner-private
+-- messages carry the channel platform (e.g. 'weixin-ilink', 'qq-obv11', 'telegram').
+--
+-- The 0003 chat_messages table already exists at this point, so ALTER ADD COLUMN is
+-- the correct, non-destructive step. The canonical schema (including this column) is
+-- also re-issued idempotently by internal/runtime/history.NewStore so a fresh
+-- in-memory store used by tests stays self-contained; the migration is the
+-- authoritative path for an existing database.
+
+ALTER TABLE chat_messages ADD COLUMN platform TEXT NOT NULL DEFAULT 'web';

internal/db/migrations/0005_chat_device.down.sql

@@ -0,0 +1,4 @@
+-- 0005_chat_device down: drop the device_id column.
+-- SQLite DROP COLUMN is supported on modern versions; rebuild safely when needed.
+
+ALTER TABLE chat_messages DROP COLUMN device_id;

internal/db/migrations/0005_chat_device.up.sql

@@ -0,0 +1,10 @@
+-- 0005_chat_device: tag every chat message with a short deviceID/client identifier
+-- (DevDocs/design/16 §4.5). deviceID is the concrete client (browser/app/IM channel
+-- binding) that produced the message, complementing `platform` which only names
+-- the platform. It lets the agent know exactly HOW the owner is chatting (e.g.
+-- "web:chrome:a1b2c3" for a browser, "weixin-ilink:conf0:wx_uid_123" for IM).
+--
+-- The 0004 chat_messages table already exists at this point, so ALTER ADD COLUMN is
+-- the correct, non-destructive step.
+
+ALTER TABLE chat_messages ADD COLUMN device_id TEXT NOT NULL DEFAULT '';

internal/runtime/history/store.go

@@ -37,6 +37,11 @@ const (
 	// SessionMain and SessionSub classify a persistent session.
 	SessionMain = "main"
 	SessionSub  = "sub"
+
+	// PlatformWeb is the source-platform tag for messages that originate on the Web
+	// main session (design/16 §4.4). It is both the column default and the value
+	// assigned when a caller leaves Message.Platform empty.
+	PlatformWeb = "web"
 )
 
 // MainSessionID is the fixed id of the one main session (design/16 §2.1). Sub session
@@ -71,6 +76,17 @@ type Message struct {
 	Mood      string
 	Image     string
 	Thinking  string
+	// Platform tags the source platform of a message (design/16 §4.4). The Web main
+	// session is shared across platforms: messages that originate on the Web carry
+	// "web", while IM-owner-private messages carry the channel platform (e.g.
+	// "telegram", "qq-obv11", "weixin-ilink"). An empty Platform defaults to "web" so
+	// legacy/explicitly-Web writes stay on the Web lane without a separate assignment.
+	Platform string
+	// DeviceID is a short, client-produced identifier for the concrete device/app
+	// that sent the message (design/16 §4.5) — e.g. "web:chrome:a1b2c3" for a
+	// browser, "weixin-ilink:conf0:wx_uid_123" for IM. It complements Platform: two
+	// clients on the same platform share Platform but differ in DeviceID.
+	DeviceID  string
 	CreatedAt int64
 }
 
@@ -92,8 +108,12 @@ type HistoryStore interface {
 	AppendFull(ctx context.Context, msg Message) (Message, error)
 	// List returns up to limit messages for sessionID, newest first. before is a
 	// millisecond timestamp cursor: when nonzero, only messages older than before are
-	// returned (inclusive-free, matching the "before" bound on the frontend).
-	List(ctx context.Context, sessionID string, before int64, limit int) ([]Message, error)
+	// returned (inclusive-free, matching the "before" bound on the frontend). platform
+	// is an optional source-platform filter (design/16 §4.4): when non-empty only
+	// messages carrying that platform are returned; when empty all platforms are
+	// returned (the Web client requests the full main session, an IM adapter asks for
+	// its own platform only).
+	List(ctx context.Context, sessionID string, before int64, limit int, platform string) ([]Message, error)
 	// Recent returns the most recent n messages for sessionID in oldest-first order,
 	// for WS replay / context tail usage.
 	Recent(ctx context.Context, sessionID string, n int) ([]Message, error)
@@ -175,11 +195,14 @@ func (s *Store) insert(ctx context.Context, msg Message) (Message, error) {
 	if msg.CreatedAt == 0 {
 		msg.CreatedAt = time.Now().UnixMilli()
 	}
+	if msg.Platform == "" {
+		msg.Platform = PlatformWeb
+	}
 	_, err := s.db.ExecContext(ctx, `INSERT INTO chat_messages
-		(id, session_id, role, content, mode, mood, image, thinking, created_at)
-		VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)`,
+		(id, session_id, role, content, mode, mood, image, thinking, platform, device_id, created_at)
+		VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)`,
 		msg.ID, msg.SessionID, msg.Role, msg.Content, msg.Mode, msg.Mood,
-		msg.Image, msg.Thinking, msg.CreatedAt)
+		msg.Image, msg.Thinking, msg.Platform, msg.DeviceID, msg.CreatedAt)
 	if err != nil {
 		return Message{}, fmt.Errorf("history: append %s to %s: %w", msg.Role, msg.SessionID, err)
 	}
@@ -188,17 +211,24 @@ func (s *Store) insert(ctx context.Context, msg Message) (Message, error) {
 
 // List returns up to limit messages for sessionID, newest first. When before is nonzero
 // it bounds the query to messages strictly older than before, so a client can page upward
-// by passing the oldest message's created_at from the previous page. The returned slice
-// is non-nil. limit is clamped to [1, maxPageLimit].
-func (s *Store) List(ctx context.Context, sessionID string, before int64, limit int) ([]Message, error) {
+// by passing the oldest message's created_at from the previous page. When platform is
+// non-empty it further restricts the page to messages carrying that source platform
+// (design/16 §4.4: the Web client omits platform for the full main session, an IM
+// adapter passes its own platform to see only its lane). The returned slice is non-nil.
+// limit is clamped to [1, maxPageLimit].
+func (s *Store) List(ctx context.Context, sessionID string, before int64, limit int, platform string) ([]Message, error) {
 	limit = clampLimit(limit)
-	query := `SELECT id, session_id, role, content, mode, mood, image, thinking, created_at
+	query := `SELECT id, session_id, role, content, mode, mood, image, thinking, platform, device_id, created_at
 		FROM chat_messages WHERE session_id = ?`
 	args := []any{sessionID}
 	if before > 0 {
 		query += ` AND created_at < ?`
 		args = append(args, before)
 	}
+	if platform != "" {
+		query += ` AND platform = ?`
+		args = append(args, platform)
+	}
 	query += ` ORDER BY created_at DESC LIMIT ?`
 	args = append(args, limit)
 
@@ -228,7 +258,7 @@ func (s *Store) Recent(ctx context.Context, sessionID string, n int) ([]Message,
 	if n < 1 {
 		n = defaultPageLimit
 	}
-	rows, err := s.db.QueryContext(ctx, `SELECT id, session_id, role, content, mode, mood, image, thinking, created_at
+	rows, err := s.db.QueryContext(ctx, `SELECT id, session_id, role, content, mode, mood, image, thinking, platform, device_id, created_at
 		FROM chat_messages WHERE session_id = ? ORDER BY created_at DESC LIMIT ?`, sessionID, n)
 	if err != nil {
 		return nil, fmt.Errorf("history: recent %s: %w", sessionID, err)
@@ -342,11 +372,11 @@ func (s *Store) ensureMainSession(ctx context.Context) error {
 // scanMessage reads one chat_messages row. message columns are scanned positionally.
 func scanMessage(sc rowScanner) (Message, error) {
 	var m Message
-	var mode, mood, image, thinking string
-	if err := sc.Scan(&m.ID, &m.SessionID, &m.Role, &m.Content, &mode, &mood, &image, &thinking, &m.CreatedAt); err != nil {
+	var mode, mood, image, thinking, platform, deviceID string
+	if err := sc.Scan(&m.ID, &m.SessionID, &m.Role, &m.Content, &mode, &mood, &image, &thinking, &platform, &deviceID, &m.CreatedAt); err != nil {
 		return Message{}, err
 	}
-	m.Mode, m.Mood, m.Image, m.Thinking = mode, mood, image, thinking
+	m.Mode, m.Mood, m.Image, m.Thinking, m.Platform, m.DeviceID = mode, mood, image, thinking, platform, deviceID
 	return m, nil
 }
 
@@ -401,6 +431,8 @@ CREATE TABLE IF NOT EXISTS chat_messages (
     mood       TEXT,
     image      TEXT,
     thinking   TEXT,
+    platform   TEXT NOT NULL DEFAULT 'web',
+    device_id  TEXT NOT NULL DEFAULT '',
     created_at INTEGER NOT NULL
 )`
 

internal/runtime/history/store_test.go

@@ -51,7 +51,7 @@ func TestAppendAndListNewestFirst(t *testing.T) {
 		}
 	}
 
-	msgs, err := st.List(ctx, MainSessionID, 0, 50)
+	msgs, err := st.List(ctx, MainSessionID, 0, 50, "")
 	if err != nil {
 		t.Fatalf("list: %v", err)
 	}
@@ -67,7 +67,7 @@ func TestAppendAndListNewestFirst(t *testing.T) {
 	if err := st.Append(ctx, empty); err != nil {
 		t.Fatalf("append no ts: %v", err)
 	}
-	msgs, err = st.List(ctx, MainSessionID, 0, 50)
+	msgs, err = st.List(ctx, MainSessionID, 0, 50, "")
 	if err != nil {
 		t.Fatalf("list after append: %v", err)
 	}
@@ -96,7 +96,7 @@ func TestAppendFullReturnsID(t *testing.T) {
 	}
 
 	// The message is actually persisted under the returned id.
-	msgs, err := st.List(ctx, MainSessionID, 0, 50)
+	msgs, err := st.List(ctx, MainSessionID, 0, 50, "")
 	if err != nil {
 		t.Fatalf("list: %v", err)
 	}
@@ -114,6 +114,133 @@ func TestAppendFullReturnsID(t *testing.T) {
 	}
 }
 
+func TestAppendFullListPlatformRoundTrip(t *testing.T) {
+	t.Parallel()
+	st := newStore(t)
+	ctx := context.Background()
+
+	// An IM owner-private message carries its channel platform through the round
+	// trip: AppendFull → List.
+	full, err := st.AppendFull(ctx, Message{SessionID: MainSessionID, Role: RoleUser, Content: "从微信来", Platform: "weixin-ilink"})
+	if err != nil {
+		t.Fatalf("append full: %v", err)
+	}
+	if full.Platform != "weixin-ilink" {
+		t.Fatalf("AppendFull platform = %q, want weixin-ilink", full.Platform)
+	}
+	msgs, err := st.List(ctx, MainSessionID, 0, 50, "")
+	if err != nil {
+		t.Fatalf("list: %v", err)
+	}
+	if len(msgs) != 1 || msgs[0].Platform != "weixin-ilink" || msgs[0].Content != "从微信来" {
+		t.Fatalf("list round trip = %+v, want platform weixin-ilink", msgs)
+	}
+
+	// A message without an explicit platform defaults to the web lane.
+	web, err := st.AppendFull(ctx, Message{SessionID: MainSessionID, Role: RoleAssistant, Content: "ok"})
+	if err != nil {
+		t.Fatalf("append web default: %v", err)
+	}
+	if web.Platform != PlatformWeb {
+		t.Fatalf("default platform = %q, want web", web.Platform)
+	}
+}
+
+func TestAppendFullListDeviceIDRoundTrip(t *testing.T) {
+	t.Parallel()
+	st := newStore(t)
+	ctx := context.Background()
+
+	// A Web message tagged with a browser deviceID survives the AppendFull → List
+	// round trip (design/16 §4.5).
+	full, err := st.AppendFull(ctx, Message{SessionID: MainSessionID, Role: RoleUser, Content: "来自浏览器", DeviceID: "web:chrome:a1b2c3"})
+	if err != nil {
+		t.Fatalf("append full: %v", err)
+	}
+	if full.DeviceID != "web:chrome:a1b2c3" {
+		t.Fatalf("AppendFull DeviceID = %q, want web:chrome:a1b2c3", full.DeviceID)
+	}
+	msgs, err := st.List(ctx, MainSessionID, 0, 50, "")
+	if err != nil {
+		t.Fatalf("list: %v", err)
+	}
+	if len(msgs) != 1 || msgs[0].DeviceID != "web:chrome:a1b2c3" || msgs[0].Content != "来自浏览器" {
+		t.Fatalf("list round trip = %+v, want DeviceID web:chrome:a1b2c3", msgs)
+	}
+
+	// Recent (WS replay / context tail) reads the same device_id column.
+	recent, err := st.Recent(ctx, MainSessionID, 5)
+	if err != nil {
+		t.Fatalf("recent: %v", err)
+	}
+	if len(recent) != 1 || recent[0].DeviceID != "web:chrome:a1b2c3" {
+		t.Fatalf("recent = %+v, want DeviceID web:chrome:a1b2c3", recent)
+	}
+
+	// A message without an explicit deviceID persists the column default ('').
+	om, err := st.AppendFull(ctx, Message{SessionID: MainSessionID, Role: RoleAssistant, Content: "ok"})
+	if err != nil {
+		t.Fatalf("append empty device: %v", err)
+	}
+	if om.DeviceID != "" {
+		t.Fatalf("empty DeviceID = %q, want empty", om.DeviceID)
+	}
+}
+
+func TestListPlatformFilter(t *testing.T) {
+	t.Parallel()
+	st := newStore(t)
+	ctx := context.Background()
+
+	// Seed across the web lane (explicit + default) and one IM lane.
+	for _, m := range []Message{
+		{SessionID: MainSessionID, Role: RoleUser, Content: "web1", Platform: PlatformWeb, CreatedAt: 1000},
+		{SessionID: MainSessionID, Role: RoleUser, Content: "tg", Platform: "telegram", CreatedAt: 2000},
+		{SessionID: MainSessionID, Role: RoleUser, Content: "web2", CreatedAt: 3000},
+	} {
+		if err := st.Append(ctx, m); err != nil {
+			t.Fatalf("seed %q: %v", m.Content, err)
+		}
+	}
+
+	// No platform filter → all three (the empty-platform message defaulted to web).
+	all, err := st.List(ctx, MainSessionID, 0, 50, "")
+	if err != nil {
+		t.Fatalf("list all: %v", err)
+	}
+	if len(all) != 3 {
+		t.Fatalf("all = %d, want 3", len(all))
+	}
+
+	// Filter to the IM lane → only its message.
+	tg, err := st.List(ctx, MainSessionID, 0, 50, "telegram")
+	if err != nil {
+		t.Fatalf("list telegram: %v", err)
+	}
+	if len(tg) != 1 || tg[0].Content != "tg" {
+		t.Fatalf("telegram page = %+v, want [tg]", tg)
+	}
+
+	// Filter to the web lane → web1 + web2 (the one left without an explicit
+	// platform defaulted to web on insert).
+	web, err := st.List(ctx, MainSessionID, 0, 50, PlatformWeb)
+	if err != nil {
+		t.Fatalf("list web: %v", err)
+	}
+	if len(web) != 2 {
+		t.Fatalf("web page = %d, want 2 (%+v)", len(web), web)
+	}
+
+	// The filter composes with the before cursor.
+	older, err := st.List(ctx, MainSessionID, 2000, 50, PlatformWeb)
+	if err != nil {
+		t.Fatalf("list web before: %v", err)
+	}
+	if len(older) != 1 || older[0].Content != "web1" {
+		t.Fatalf("web before page = %+v, want [web1]", older)
+	}
+}
+
 func TestListPaginationBefore(t *testing.T) {
 	t.Parallel()
 	st := newStore(t)
@@ -126,7 +253,7 @@ func TestListPaginationBefore(t *testing.T) {
 	}
 
 	// First page: newest 2.
-	page, err := st.List(ctx, MainSessionID, 0, 2)
+	page, err := st.List(ctx, MainSessionID, 0, 2, "")
 	if err != nil {
 		t.Fatalf("first page: %v", err)
 	}
@@ -134,7 +261,7 @@ func TestListPaginationBefore(t *testing.T) {
 		t.Fatalf("first page = %+v, want [6000 5000]", page)
 	}
 	// Cursor on the page's oldest (5000) → older page [4000 3000].
-	next, err := st.List(ctx, MainSessionID, page[1].CreatedAt, 2)
+	next, err := st.List(ctx, MainSessionID, page[1].CreatedAt, 2, "")
 	if err != nil {
 		t.Fatalf("next page: %v", err)
 	}
@@ -142,7 +269,7 @@ func TestListPaginationBefore(t *testing.T) {
 		t.Fatalf("next page = %+v, want [4000 3000]", next)
 	}
 	// Past the start → empty.
-	tail, err := st.List(ctx, MainSessionID, 1000, 50)
+	tail, err := st.List(ctx, MainSessionID, 1000, 50, "")
 	if err != nil {
 		t.Fatalf("tail: %v", err)
 	}
@@ -220,7 +347,7 @@ func TestDeleteSession(t *testing.T) {
 	if err := st.DeleteSession(ctx, sub); err != nil {
 		t.Fatalf("delete sub: %v", err)
 	}
-	msgs, err := st.List(ctx, sub, 0, 50)
+	msgs, err := st.List(ctx, sub, 0, 50, "")
 	if err != nil {
 		t.Fatalf("list after delete: %v", err)
 	}

internal/services/channelbridge/channelbridge.go

@@ -24,6 +24,7 @@ import (
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/channel/adapter"
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/channel/session"
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/logger"
+	"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"
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/user"
@@ -72,21 +73,30 @@ type SessionStore interface {
 
 // Options carries the bridge's injected dependencies. Loop and Sessions are
 // required; Owner may be nil (then no account is recognized as owner, the safe
-// default-deny posture from design/11 §0).
+// default-deny posture from design/11 §0). History and OnPersisted are optional
+// (design/16 §4.4): when a history store is wired, owner-private messages are
+// routed into the main web session and tagged with the channel platform, and every
+// persisted message is handed to OnPersisted so the gateway can broadcast a
+// `message_persisted` event; when both are absent the bridge runs exactly as
+// before (isolated sess-xxx, no chat_messages writes).
 type Options struct {
-	Log      *slog.Logger
-	Loop     Chatter
-	Sessions SessionStore
-	Owner    *user.OwnerProfile
+	Log         *slog.Logger
+	Loop        Chatter
+	Sessions    SessionStore
+	Owner       *user.OwnerProfile
+	History     history.HistoryStore
+	OnPersisted func(history.Message)
 }
 
 // Bridge owns the channel adapter lifecycle and the inbound message pipeline. It
 // is safe for concurrent use.
 type Bridge struct {
-	log      *slog.Logger
-	run      Chatter
-	sessions SessionStore
-	owner    *user.OwnerProfile
+	log         *slog.Logger
+	run         Chatter
+	sessions    SessionStore
+	owner       *user.OwnerProfile
+	history     history.HistoryStore
+	onPersisted func(history.Message)
 
 	mu        sync.RWMutex
 	adapters  map[string]adapter.PlatformAdapter
@@ -114,14 +124,16 @@ func New(opts Options) (*Bridge, error) {
 		log = logger.New(logger.Options{Out: nil})
 	}
 	return &Bridge{
-		log:       logger.WithSource(log, "services/channelbridge"),
-		run:       opts.Loop,
-		sessions:  opts.Sessions,
-		owner:     opts.Owner,
-		adapters:  make(map[string]adapter.PlatformAdapter),
-		connected: make(map[string]bool),
-		cancel:    func() {},
-		sem:       make(chan struct{}, maxConcurrent),
+		log:         logger.WithSource(log, "services/channelbridge"),
+		run:         opts.Loop,
+		sessions:    opts.Sessions,
+		owner:       opts.Owner,
+		history:     opts.History,
+		onPersisted: opts.OnPersisted,
+		adapters:    make(map[string]adapter.PlatformAdapter),
+		connected:   make(map[string]bool),
+		cancel:      func() {},
+		sem:         make(chan struct{}, maxConcurrent),
 	}, nil
 }
 
@@ -353,28 +365,52 @@ func (b *Bridge) process(ctx context.Context, msg adapter.UnifiedMessage) {
 		"session", sess.SessionID, "actor_role", sess.ActorRole,
 		"env", sess.Env(), "mem_writable", sess.MemWritable)
 
+	// design/16 §4.4 + design/02 §3: an owner private chat is routed INTO the single
+	// main web session (shared across platforms) and persisted to chat_messages with
+	// the channel platform, so the Web client mirrors it; group chats and strangers
+	// keep their isolated sess-xxx context and are NOT persisted to the main session.
+	sessID := sess.SessionID
+	isOwnerPrivate := !sess.IsGroup && sess.Owner
+	platform := ""
+	if isOwnerPrivate {
+		sessID = history.MainSessionID
+		platform = msg.Platform
+	}
+
+	// Persist the inbound user message into the main web session before the turn, so
+	// the Web client sees it even if the channel reply fails (design/16 §4.4).
+	if isOwnerPrivate {
+		b.persistToMain(ctx, history.RoleUser, text, platform, deviceIDFor(msg))
+	}
+
 	// Thread the resolved isolation boundary into the loop's memory gates: the
 	// owner's private conversation reads+writes memory, group chats and strangers
 	// are read-only isolation (design/02 §3, design/11 §2).
 	runEnv := loop.SessionEnv{ActorEnv: sess.Env(), MemWritable: sess.MemWritable}
-	res, err := b.run.Run(loop.WithSessionEnv(ctx, runEnv), sess.SessionID, []model.Message{
+	res, err := b.run.Run(loop.WithSessionEnv(ctx, runEnv), sessID, []model.Message{
 		model.TextMessage(model.RoleUser, text),
 	})
 	if err != nil {
 		b.log.Warn("agent run failed", "platform", msg.Platform,
-			"session", sess.SessionID, "error", err)
+			"session", sessID, "error", err)
 		return
 	}
 
 	reply := strings.TrimSpace(res.Text)
 	if reply == "" {
-		b.log.Debug("no reply produced", "platform", msg.Platform, "session", sess.SessionID)
+		b.log.Debug("no reply produced", "platform", msg.Platform, "session", sessID)
 		return
 	}
+	// Persist the assistant reply into the main web session (design/16 §4.4) and
+	// broadcast, then deliver it back to the channel — so the Web client mirrors the
+	// IM reply too.
+	if isOwnerPrivate {
+		b.persistToMain(ctx, history.RoleAssistant, reply, platform, deviceIDFor(msg))
+	}
 	if err := b.sendReply(ctx, msg, reply); err != nil {
 		if errors.Is(err, adapter.ErrUnsupported) {
 			b.log.Debug("channel does not support outbound reply, skipped",
-				"platform", msg.Platform, "session", sess.SessionID)
+				"platform", msg.Platform, "session", sessID)
 			return
 		}
 		b.log.Warn("send reply failed", "platform", msg.Platform, "error", err)
@@ -422,3 +458,20 @@ func cfgStr(m map[string]any, key string) string {
 	}
 	return ""
 }
+
+// deviceIDFor builds the client deviceID tag for an inbound IM message
+// (design/16 §4.5): <im平台名>:<本地配置唯一id>:<用户平台唯一uid>. UnifiedMessage has no
+// explicit deviceId field yet, so the local config id and the user platform uid are
+// taken from the normalized channel binding: ChannelID stands in for the local
+// adapter binding and SenderID is the owner's platform uid. When SenderID is absent
+// the tag degrades to <platform>:<channelID> so it stays non-empty and readable.
+//
+// Extension point: when an adapter/UnifiedMessage grows a concrete deviceId (or the
+// bridge gains a local config id), replace the ChannelID stand-in here and return
+// that value directly.
+func deviceIDFor(msg adapter.UnifiedMessage) string {
+	if msg.SenderID != "" {
+		return msg.Platform + ":" + msg.ChannelID + ":" + msg.SenderID
+	}
+	return msg.Platform + ":" + msg.ChannelID
+}

internal/services/channelbridge/channelbridge_test.go

@@ -2,10 +2,12 @@ package channelbridge
 
 import (
 	"context"
+	"sync"
 	"testing"
 
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/channel/adapter"
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/channel/session"
+	"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"
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/user"
@@ -113,8 +115,9 @@ func TestProcessRunsPipelineAndReplies(t *testing.T) {
 	if sess.msg.SenderID != "100" {
 		t.Errorf("resolved sender = %q, want 100", sess.msg.SenderID)
 	}
-	if chat.sessionID != "sess-1" {
-		t.Errorf("loop session id = %q, want sess-1", chat.sessionID)
+	// An owner private chat routes into the single main web session (design/16 §4.4).
+	if chat.sessionID != history.MainSessionID {
+		t.Errorf("loop session id = %q, want %q", chat.sessionID, history.MainSessionID)
 	}
 	if len(chat.messages) != 1 || chat.messages[0].Role != model.RoleUser {
 		t.Fatalf("loop messages = %+v, want single user message", chat.messages)
@@ -160,8 +163,8 @@ func TestProcessLoopErrorDoesNotSend(t *testing.T) {
 
 	b.process(context.Background(), directMessage())
 
-	if chat.sessionID != "sess-1" {
-		t.Errorf("loop should still run for valid text, session = %q", chat.sessionID)
+	if chat.sessionID != history.MainSessionID {
+		t.Errorf("loop should still run for valid text on the main session, session = %q", chat.sessionID)
 	}
 	if len(ad.sends) != 0 {
 		t.Errorf("send count = %d, want 0 on loop error", len(ad.sends))
@@ -207,3 +210,165 @@ func TestProcessEmptyReplySendsNothing(t *testing.T) {
 		t.Errorf("send count = %d, want 0 for empty reply", len(ad.sends))
 	}
 }
+
+// captureHistory records every Append for asserting the bridge writes owner-private
+// messages into the main web session (design/16 §4.4).
+type captureHistory struct {
+	mu      sync.Mutex
+	appends []history.Message
+}
+
+func (c *captureHistory) Append(_ context.Context, msg history.Message) error {
+	_, err := c.AppendFull(context.Background(), msg)
+	return err
+}
+
+func (c *captureHistory) AppendFull(_ context.Context, msg history.Message) (history.Message, error) {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+	c.appends = append(c.appends, msg)
+	return msg, nil
+}
+
+func (c *captureHistory) List(context.Context, string, int64, int, string) ([]history.Message, error) {
+	return nil, nil
+}
+func (c *captureHistory) Recent(context.Context, string, int) ([]history.Message, error) {
+	return nil, nil
+}
+func (c *captureHistory) DeleteSession(context.Context, string) error { return nil }
+func (c *captureHistory) NewSubSession(context.Context, string) (string, error) {
+	return "", nil
+}
+func (c *captureHistory) ListSessions(context.Context) ([]history.SessionMeta, error) {
+	return nil, nil
+}
+
+func (c *captureHistory) records() []history.Message {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+	return append([]history.Message(nil), c.appends...)
+}
+
+func TestOwnerPrivatePersistsToMainSessionWithPlatform(t *testing.T) {
+	t.Parallel()
+
+	chat := &stubChatter{res: &loop.Result{Text: "微信回复"}}
+	sess := &stubSessions{sess: session.Session{SessionID: "sess-1", Owner: true, MemWritable: true}}
+	hist := &captureHistory{}
+	var persisted []history.Message
+	b, err := New(Options{
+		Loop: chat, Sessions: sess, Owner: &user.OwnerProfile{},
+		History:     hist,
+		OnPersisted: func(m history.Message) { persisted = append(persisted, m) },
+	})
+	if err != nil {
+		t.Fatalf("New: %v", err)
+	}
+
+	msg := directMessage() // Platform = "telegram"
+	b.process(context.Background(), msg)
+
+	recs := hist.records()
+	if len(recs) != 2 {
+		t.Fatalf("appends = %d, want 2 (user + assistant)", len(recs))
+	}
+	// Both land on the main web session and carry the channel platform.
+	if recs[0].SessionID != history.MainSessionID || recs[0].Role != history.RoleUser ||
+		recs[0].Content != "hello" || recs[0].Platform != "telegram" {
+		t.Fatalf("user record = %+v, want web/telegram/hello", recs[0])
+	}
+	if recs[1].SessionID != history.MainSessionID || recs[1].Role != history.RoleAssistant ||
+		recs[1].Content != "微信回复" || recs[1].Platform != "telegram" {
+		t.Fatalf("assistant record = %+v, want web/telegram/微信回复", recs[1])
+	}
+	// Every persisted message was handed to the broadcast hook.
+	if len(persisted) != 2 {
+		t.Fatalf("persisted notifications = %d, want 2", len(persisted))
+	}
+	// And the loop ran against the main session, not the isolated sess-1.
+	if chat.sessionID != history.MainSessionID {
+		t.Fatalf("loop session id = %q, want %q", chat.sessionID, history.MainSessionID)
+	}
+}
+
+func TestOwnerPrivatePersistsToMainWithDeviceID(t *testing.T) {
+	t.Parallel()
+
+	chat := &stubChatter{res: &loop.Result{Text: "微信回复"}}
+	sess := &stubSessions{sess: session.Session{SessionID: "sess-1", Owner: true, MemWritable: true}}
+	hist := &captureHistory{}
+	b, err := New(Options{
+		Loop: chat, Sessions: sess, Owner: &user.OwnerProfile{},
+		History: hist,
+	})
+	if err != nil {
+		t.Fatalf("New: %v", err)
+	}
+
+	// directMessage() → Platform telegram / ChannelID 100 / SenderID 100, so the
+	// deviceID is built as <platform>:<channelID>:<senderID> (design/16 §4.5).
+	b.process(context.Background(), directMessage())
+
+	recs := hist.records()
+	if len(recs) != 2 {
+		t.Fatalf("appends = %d, want 2 (user + assistant)", len(recs))
+	}
+	// Both the user turn and the assistant reply carry the derived deviceID and the
+	// channel platform, so the Web client can label the source end.
+	for i, rec := range recs {
+		if rec.DeviceID != "telegram:100:100" {
+			t.Fatalf("record[%d] DeviceID = %q, want telegram:100:100", i, rec.DeviceID)
+		}
+		if rec.Platform != "telegram" {
+			t.Fatalf("record[%d] Platform = %q, want telegram", i, rec.Platform)
+		}
+	}
+	if recs[0].Role != history.RoleUser || recs[0].Content != "hello" {
+		t.Fatalf("user record = %+v", recs[0])
+	}
+	if recs[1].Role != history.RoleAssistant || recs[1].Content != "微信回复" {
+		t.Fatalf("assistant record = %+v", recs[1])
+	}
+}
+
+func TestGroupMessageNotPersistedToMainSession(t *testing.T) {
+	t.Parallel()
+
+	chat := &stubChatter{res: &loop.Result{Text: "群聊回复"}}
+	sess := &stubSessions{sess: session.Session{SessionID: "sess-g", IsGroup: true, Owner: true, MemWritable: false}}
+	hist := &captureHistory{}
+	b, err := New(Options{Loop: chat, Sessions: sess, Owner: &user.OwnerProfile{}, History: hist})
+	if err != nil {
+		t.Fatalf("New: %v", err)
+	}
+
+	msg := adapter.UnifiedMessage{
+		Platform: "telegram", ChannelID: "-20", ChannelType: adapter.ChannelGroup,
+		GroupID: "-20", GroupName: "Gang", SenderID: "9", Content: "hello all",
+		ContentType: adapter.ContentText,
+	}
+	b.process(context.Background(), msg)
+
+	// Group chat stays isolated: nothing is written to the main web session and the
+	// loop runs against the isolated session id.
+	if recs := hist.records(); len(recs) != 0 {
+		t.Fatalf("group appends = %+v, want none persisted", recs)
+	}
+	if chat.sessionID != "sess-g" {
+		t.Fatalf("group loop session id = %q, want sess-g", chat.sessionID)
+	}
+}
+
+func TestNoHistoryStoreKeepsBridgeUnchanged(t *testing.T) {
+	t.Parallel()
+	// A bridge built without a history store persists nothing but still runs/replies.
+	b, chat, _, ad := newTestBridge(t)
+	b.process(context.Background(), directMessage())
+	if len(ad.sends) != 1 {
+		t.Fatalf("send count = %d, want 1", len(ad.sends))
+	}
+	if chat.sessionID != history.MainSessionID {
+		t.Fatalf("loop session id = %q, want %q", chat.sessionID, history.MainSessionID)
+	}
+}

internal/services/channelbridge/persist.go

@@ -0,0 +1,55 @@
+package channelbridge
+
+import (
+	"context"
+
+	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/history"
+)
+
+// This file holds the channelbridge's chat-history persistence hooks (design/16
+// §4.4): an owner private chat is routed INTO the single main web session and
+// tagged with the channel platform, then broadcast so the Web client mirrors it
+// without a refresh. Kept separate from channelbridge.go so the bridge's inbound
+// pipeline file stays under the module size bound.
+
+// SetOnPersisted wires (or replaces) the transport hook called after an
+// owner-private message is persisted into the main web session. The gateway is
+// built after the bridge in the composition root, so the hook is attached post-New
+// through this setter; it is a no-op-safe call and is safe for concurrent use with
+// in-flight processing.
+func (b *Bridge) SetOnPersisted(fn func(history.Message)) {
+	b.mu.Lock()
+	defer b.mu.Unlock()
+	b.onPersisted = fn
+}
+
+// notifyPersisted hands a just-persisted message to the transport hook when one is
+// wired, so the gateway can broadcast `message_persisted` for cross-end sync.
+func (b *Bridge) notifyPersisted(msg history.Message) {
+	b.mu.RLock()
+	fn := b.onPersisted
+	b.mu.RUnlock()
+	if fn != nil {
+		fn(msg)
+	}
+}
+
+// persistToMain writes one message into the main web session with an explicit source
+// platform and client deviceID, then notifies the transport hook so Web clients receive
+// a `message_persisted` event without a refresh (design/16 §4.4). deviceID is the
+// concrete client that sent the message (design/16 §4.5) — e.g. "weixin-ilink:conf0:wx_uid"
+// for IM. It is a no-op when no history store is wired, so the bridge runs unchanged
+// without storage.
+func (b *Bridge) persistToMain(ctx context.Context, role, content, platform, deviceID string) {
+	if b.history == nil {
+		return
+	}
+	full, err := b.history.AppendFull(ctx, history.Message{
+		SessionID: history.MainSessionID, Role: role, Content: content, Platform: platform, DeviceID: deviceID,
+	})
+	if err != nil {
+		b.log.Warn("persist main session", "err", err, "role", role, "platform", platform, "device_id", deviceID)
+		return
+	}
+	b.notifyPersisted(full)
+}

internal/services/gateway/history.go

@@ -32,6 +32,8 @@ type historyMessage struct {
 	Mood      string `json:"mood,omitempty"`
 	Image     string `json:"image,omitempty"`
 	Thinking  string `json:"thinking,omitempty"`
+	Platform  string `json:"platform,omitempty"`
+	DeviceID  string `json:"deviceId,omitempty"`
 	CreatedAt int64  `json:"createdAt"`
 }
 
@@ -108,8 +110,9 @@ func (s *Server) handleListMessages(w http.ResponseWriter, r *http.Request) {
 		}
 		before = v
 	}
+	platform := r.URL.Query().Get("platform")
 
-	msgs, err := s.history.List(r.Context(), id, before, limit)
+	msgs, err := s.history.List(r.Context(), id, before, limit, platform)
 	if err != nil {
 		s.log.Error("history list messages", "err", err, "session", id)
 		writeError(w, apperr.Wrap(apperr.ErrInternal, "messages_failed", "failed to list messages"))
@@ -157,6 +160,8 @@ func toHistoryMessage(m history.Message) historyMessage {
 		Mood:      m.Mood,
 		Image:     m.Image,
 		Thinking:  m.Thinking,
+		Platform:  m.Platform,
+		DeviceID:  m.DeviceID,
 		CreatedAt: m.CreatedAt,
 	}
 }

internal/services/gateway/history_handler_test.go

@@ -133,6 +133,41 @@ func TestHistoryListMessagesPagination(t *testing.T) {
 	}
 }
 
+func TestHistoryListMessagesPlatformFilter(t *testing.T) {
+	t.Parallel()
+	_, ts, jwt, st := newHistoryEnv(t)
+	ctx := context.Background()
+	if err := st.Append(ctx, history.Message{SessionID: history.MainSessionID, Role: history.RoleUser, Content: "web", Platform: history.PlatformWeb, CreatedAt: 1000}); err != nil {
+		t.Fatalf("seed web: %v", err)
+	}
+	if err := st.Append(ctx, history.Message{SessionID: history.MainSessionID, Role: history.RoleUser, Content: "tg", Platform: "telegram", CreatedAt: 2000}); err != nil {
+		t.Fatalf("seed tg: %v", err)
+	}
+	tok := signAny(t, jwt, "acct", auth.RoleOwner)
+
+	// No platform → the full main session (both lanes).
+	resp, body := doReq(t, http.MethodGet, ts.URL+"/api/v1/sessions/"+history.MainSessionID+"/messages?limit=10", nil, tok)
+	if resp.StatusCode != http.StatusOK {
+		t.Fatalf("all status = %d, want 200 (body=%s)", resp.StatusCode, body)
+	}
+	var all []historyMessage
+	decodeDataSlice(t, body, &all)
+	if len(all) != 2 {
+		t.Fatalf("all = %d, want 2", len(all))
+	}
+
+	// ?platform=telegram → only the telegram lane, and the DTO carries platform.
+	resp, body = doReq(t, http.MethodGet, ts.URL+"/api/v1/sessions/"+history.MainSessionID+"/messages?limit=10&platform=telegram", nil, tok)
+	if resp.StatusCode != http.StatusOK {
+		t.Fatalf("platform status = %d, want 200 (body=%s)", resp.StatusCode, body)
+	}
+	var tg []historyMessage
+	decodeDataSlice(t, body, &tg)
+	if len(tg) != 1 || tg[0].Content != "tg" || tg[0].Platform != "telegram" {
+		t.Fatalf("telegram page = %+v, want one platform=telegram message", tg)
+	}
+}
+
 func TestHistoryDeleteSubSession(t *testing.T) {
 	t.Parallel()
 	_, ts, jwt, st := newHistoryEnv(t)

internal/services/gateway/rest.go

@@ -70,10 +70,13 @@ type loginResponse struct {
 // triggers streaming over the WebSocket channel and returns immediately. Image is
 // an optional base64 data: URI or http(s) URL attached for the vision path; the
 // loop routes it through the vision/OCR tool or the main model (design/06 §0).
+// DeviceID is the client-produced identifier of the sending browser/device
+// (design/16 §4.5), e.g. "web:chrome:a1b2c3"; it is optional and persisted as-is.
 type chatRequest struct {
 	SessionID string `json:"sessionId"`
 	Text      string `json:"text"`
 	Image     string `json:"image,omitempty"`
+	DeviceID  string `json:"deviceId,omitempty"`
 	Stream    bool   `json:"stream"`
 }
 
@@ -126,7 +129,7 @@ func (s *Server) handleChat(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 	if req.Stream {
-		s.publishChatStream(r.Context(), req.SessionID, req.Text, req.Image)
+		s.publishChatStream(r.Context(), req.SessionID, req.Text, req.Image, req.DeviceID)
 		writeJSON(w, http.StatusOK, map[string]any{"stream": true})
 		return
 	}
@@ -141,7 +144,7 @@ func (s *Server) handleChat(w http.ResponseWriter, r *http.Request) {
 	// it binds the full-access env: memory read+write, unchanged behavior.
 	msgs := userChatMessages(req.Text, req.Image)
 	if s.hub.orchestrator != nil {
-		sr, res := s.hub.orchestrator.SubmitSync(r.Context(), req.SessionID, msgs, loop.OwnerEnv())
+		sr, res := s.hub.orchestrator.SubmitSync(withDeviceID(r.Context(), req.DeviceID), req.SessionID, msgs, loop.OwnerEnv())
 		if !sr.Accepted {
 			if sr.PendingFull {
 				writeError(w, apperr.Wrap(apperr.ErrConflict, "chat_busy", "会话正忙，待处理消息已满"))

internal/services/gateway/server.go

@@ -113,7 +113,7 @@ type HistoryStore interface {
 	// (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)
+	List(ctx context.Context, sessionID string, before int64, limit int, platform string) ([]history.Message, error)
 	Recent(ctx context.Context, sessionID string, n int) ([]history.Message, error)
 	DeleteSession(ctx context.Context, sessionID string) error
 	NewSubSession(ctx context.Context, ownerID string) (string, error)
@@ -459,20 +459,25 @@ 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,
+		OnPersisted: s.BroadcastPersisted,
+		Log:         s.log,
+		History:     s.history,
 	})
 }
 
+// BroadcastPersisted broadcasts a just-persisted chat message as a
+// `message_persisted` WS event so every browser of the same account appends it
+// without a manual refresh (design/16 §4.2). It is shared by the orchestrator
+// (Web turns) and the channel bridge (IM owner-private messages routed into the
+// main web session), so both paths emit the identical frame. Thinking is stripped
+// to stay consistent with the WS history replay (design/16 §6). It is a no-op-safe
+// call when the hub has broadcast wired.
+func (s *Server) BroadcastPersisted(msg history.Message) {
+	wire := toHistoryMessage(msg)
+	wire.Thinking = ""
+	s.hub.broadcast(wsEvent{Type: "message_persisted", SessionID: msg.SessionID, Data: map[string]any{"message": wire}})
+}
+
 // sourcedLog returns a logger tagged with source "gateway", substituting a
 // discard logger for nil so Server can always log safely.
 func sourcedLog(l *slog.Logger) *slog.Logger {

internal/services/gateway/session_orchestrator.go

@@ -128,10 +128,13 @@ type sessionState struct {
 }
 
 // pendingMsg is one queued user turn. It carries its own env so a resume runs
-// under the same memory-isolation boundary the message arrived with.
+// under the same memory-isolation boundary the message arrived with, plus the
+// client deviceID of the originating turn (design/16 §4.5) so the resumed
+// assistant reply is tagged with the same client that sent the message.
 type pendingMsg struct {
 	messages []model.Message
 	env      loop.SessionEnv
+	deviceID string
 	at       time.Time
 }
 
@@ -215,6 +218,7 @@ func (o *Orchestrator) submitInternal(ctx context.Context, sessionID string, mes
 		st = &sessionState{mode: ModeIdle}
 		o.states[sessionID] = st
 	}
+	deviceID := deviceIDFrom(ctx)
 	if st.mode != ModeIdle {
 		if len(st.pending) >= o.maxPending {
 			mode := st.mode
@@ -222,11 +226,11 @@ func (o *Orchestrator) submitInternal(ctx context.Context, sessionID string, mes
 			o.emitState(sessionID, EventPendingFull, map[string]any{"sessionId": sessionID, "mode": mode, "max": o.maxPending})
 			return SubmitResult{PendingFull: true}, nil
 		}
-		st.pending = append(st.pending, pendingMsg{messages: messages, env: env, at: time.Now()})
+		st.pending = append(st.pending, pendingMsg{messages: messages, env: env, deviceID: deviceID, at: time.Now()})
 		depth := len(st.pending)
 		mode := st.mode
 		o.mu.Unlock()
-		o.persistUserMessages(ctx, sessionID, messages)
+		o.persistUserMessages(ctx, sessionID, messages, deviceID)
 		o.emitState(sessionID, EventPendingAck, map[string]any{"sessionId": sessionID, "mode": mode, "queueDepth": depth})
 		return SubmitResult{Accepted: true, Pending: true, QueueDepth: depth}, nil
 	}
@@ -240,30 +244,32 @@ func (o *Orchestrator) submitInternal(ctx context.Context, sessionID string, mes
 	o.mu.Unlock()
 
 	o.emitState(sessionID, EventSessionBusy, map[string]any{"sessionId": sessionID, "mode": ModeThinking})
-	o.persistUserMessages(ctx, sessionID, messages)
+	o.persistUserMessages(ctx, sessionID, messages, deviceID)
 
 	if sync {
 		res, err := o.run(runCtx, sessionID, messages, env)
 		if err != nil {
 			o.log.Error("orchestrator turn", "err", err, "session", sessionID)
 		}
-		_ = o.completeTurn(sessionID, gen, res, err)
+		_ = o.completeTurn(sessionID, gen, res, err, deviceID)
 		return SubmitResult{Accepted: true, Immediate: true, Err: err}, res
 	}
 
-	go o.goTurn(sessionID, gen, messages, env, runCtx, cancel)
+	go o.goTurn(sessionID, gen, messages, env, runCtx, cancel, deviceID)
 	return SubmitResult{Accepted: true, Immediate: true}, nil
 }
 
 // goTurn runs a single turn on a background goroutine and, when it finishes,
 // hands the outcome to completeTurn so the orchestrator can resume the queue.
-func (o *Orchestrator) goTurn(sessionID string, gen uint64, messages []model.Message, env loop.SessionEnv, ctx context.Context, cancel context.CancelFunc) {
+// deviceID tags the persistent assistant reply with the client that sent the turn
+// (design/16 §4.5).
+func (o *Orchestrator) goTurn(sessionID string, gen uint64, messages []model.Message, env loop.SessionEnv, ctx context.Context, cancel context.CancelFunc, deviceID string) {
 	defer cancel()
 	res, err := o.run(ctx, sessionID, messages, env)
 	if err != nil && ctx.Err() == nil {
 		o.log.Error("orchestrator turn", "err", err, "session", sessionID)
 	}
-	_ = o.completeTurn(sessionID, gen, res, err)
+	_ = o.completeTurn(sessionID, gen, res, err, deviceID)
 }
 
 // completeTurn runs after a turn settles (either it finished, errored, or was
@@ -272,8 +278,9 @@ func (o *Orchestrator) goTurn(sessionID string, gen uint64, messages []model.Mes
 // message "remembers" the prior context instead of starting from a blank slate
 // (design/15 §2.2: incremental, not full replay). A stale generation (an
 // interrupt or a newer top-level turn superseded this one) is a no-op.
-func (o *Orchestrator) completeTurn(sessionID string, gen uint64, res *loop.Result, runErr error) error {
-	o.persistAssistantReply(sessionID, res)
+// deviceID is the originating turn's client id, used to tag the persisted reply.
+func (o *Orchestrator) completeTurn(sessionID string, gen uint64, res *loop.Result, runErr error, deviceID string) error {
+	o.persistAssistantReply(sessionID, res, deviceID)
 	o.mu.Lock()
 	st := o.states[sessionID]
 	if st == nil || st.gen != gen {
@@ -298,7 +305,7 @@ func (o *Orchestrator) completeTurn(sessionID string, gen uint64, res *loop.Resu
 		o.mu.Unlock()
 
 		o.emitState(sessionID, EventPendingDrain, map[string]any{"sessionId": sessionID, "mode": ModeThinking, "queueDepth": depth})
-		go o.goTurn(sessionID, gen, resume, env, runCtx, cancel)
+		go o.goTurn(sessionID, gen, resume, env, runCtx, cancel, next.deviceID)
 		return nil
 	}
 
@@ -430,6 +437,23 @@ func (o *Orchestrator) notifyPersisted(msg history.Message) {
 	}
 }
 
+// deviceIDContextKey is the context key carrying a message's client deviceID
+// (design/16 §4.5) from the HTTP/WS boundary into the orchestrator's persistence.
+type deviceIDContextKey struct{}
+
+// withDeviceID returns a context carrying deviceID so the orchestrator can tag the
+// persisted user message. An empty deviceID is a no-op (no tag is written).
+func withDeviceID(ctx context.Context, deviceID string) context.Context {
+	return context.WithValue(ctx, deviceIDContextKey{}, deviceID)
+}
+
+// deviceIDFrom returns the deviceID carried by ctx, or "" when none was set. It
+// returns only well-formed non-empty values; anything else is treated as absent.
+func deviceIDFrom(ctx context.Context) string {
+	v, _ := ctx.Value(deviceIDContextKey{}).(string)
+	return v
+}
+
 // boundedTail returns a fresh copy of the last maxTail messages, so continuation
 // stays incremental and bounded (design/15 §2.2, §4) and never aliases the input
 // slice or another state's tail.

internal/services/gateway/session_orchestrator_test.go

@@ -175,7 +175,7 @@ func (f *fakeHistory) AppendFull(_ context.Context, msg history.Message) (histor
 	return msg, nil
 }
 
-func (f *fakeHistory) List(context.Context, string, int64, int) ([]history.Message, error) {
+func (f *fakeHistory) List(context.Context, string, int64, int, string) ([]history.Message, error) {
 	return nil, nil
 }
 
@@ -230,6 +230,38 @@ func TestSubmitPersistsUserAndAssistant(t *testing.T) {
 	}
 }
 
+func TestSubmitPersistsDeviceID(t *testing.T) {
+	t.Parallel()
+	run := newGatedRunner(1)
+	hist := &fakeHistory{}
+	o := NewOrchestrator(OrchestratorOptions{
+		Run:     run.Run,
+		Log:     slog.Default(),
+		History: hist,
+	})
+	run.tickets <- struct{}{}
+	// The HTTP/WS boundary threads the browser deviceID through ctx (design/16 §4.5);
+	// both the user turn and the assistant reply must be tagged with it.
+	ctx := withDeviceID(context.Background(), "web:chrome:a1b2c3")
+	sr, res := o.SubmitSync(ctx, "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].Role != history.RoleUser || recs[0].Content != "你好" || recs[0].DeviceID != "web:chrome:a1b2c3" {
+		t.Fatalf("user record = %+v, want DeviceID web:chrome:a1b2c3", recs[0])
+	}
+	if recs[1].Role != history.RoleAssistant || recs[1].Content == "" || recs[1].DeviceID != "web:chrome:a1b2c3" {
+		t.Fatalf("assistant record = %+v, want DeviceID web:chrome:a1b2c3", recs[1])
+	}
+}
+
 func TestSubmitPersistedBroadcast(t *testing.T) {
 	t.Parallel()
 	run := newGatedRunner(1)

internal/services/gateway/session_persist.go

@@ -16,10 +16,11 @@ import (
 // persistUserMessages writes each RoleUser message of a submitted turn to the
 // history store so the raw user stream is durable before the turn resolves, then
 // notifies the transport so every browser of the same account can append it
-// without a manual refresh (design/16 §3.3, §4.2). It is a no-op when no history
-// store is wired. Rejected turns (empty, pending-full) never reach it, so nothing
-// vacuous is persisted.
-func (o *Orchestrator) persistUserMessages(ctx context.Context, sessionID string, messages []model.Message) {
+// without a manual refresh (design/16 §3.3, §4.2). deviceID tags the message with
+// the sending client (design/16 §4.5). It is a no-op when no history store is
+// wired. Rejected turns (empty, pending-full) never reach it, so nothing vacuous
+// is persisted.
+func (o *Orchestrator) persistUserMessages(ctx context.Context, sessionID string, messages []model.Message, deviceID string) {
 	if o.history == nil {
 		return
 	}
@@ -31,9 +32,9 @@ func (o *Orchestrator) persistUserMessages(ctx context.Context, sessionID string
 		if text == "" && image == "" {
 			continue
 		}
-		full, err := o.history.AppendFull(ctx, history.Message{SessionID: sessionID, Role: history.RoleUser, Content: text, Image: image})
+		full, err := o.history.AppendFull(ctx, history.Message{SessionID: sessionID, Role: history.RoleUser, Content: text, Image: image, DeviceID: deviceID})
 		if err != nil {
-			o.log.Error("orchestrator persist user", "err", err, "session", sessionID)
+			o.log.Error("orchestrator persist user", "err", err, "session", sessionID, "device_id", deviceID)
 			continue
 		}
 		o.notifyPersisted(full)
@@ -41,17 +42,18 @@ func (o *Orchestrator) persistUserMessages(ctx context.Context, sessionID string
 }
 
 // persistAssistantReply writes the final assistant text of a settled turn to the
-// history store, then notifies the transport (design/16 §3.3, §4.2). It is a
-// no-op when no history store is wired or the turn produced no text
-// (interrupted/errored turns leave res nil). The write runs under a fresh
-// background context so a canceled turn context never aborts it.
-func (o *Orchestrator) persistAssistantReply(sessionID string, res *loop.Result) {
+// history store, then notifies the transport (design/16 §3.3, §4.2). deviceID tags
+// the reply with the client that sent the turn (design/16 §4.5). It is a no-op
+// when no history store is wired or the turn produced no text (interrupted/errored
+// turns leave res nil). The write runs under a fresh background context so a
+// canceled turn context never aborts it.
+func (o *Orchestrator) persistAssistantReply(sessionID string, res *loop.Result, deviceID string) {
 	if o.history == nil || res == nil || res.Text == "" {
 		return
 	}
-	full, err := o.history.AppendFull(context.Background(), history.Message{SessionID: sessionID, Role: history.RoleAssistant, Content: res.Text})
+	full, err := o.history.AppendFull(context.Background(), history.Message{SessionID: sessionID, Role: history.RoleAssistant, Content: res.Text, DeviceID: deviceID})
 	if err != nil {
-		o.log.Error("orchestrator persist assistant", "err", err, "session", sessionID)
+		o.log.Error("orchestrator persist assistant", "err", err, "session", sessionID, "device_id", deviceID)
 		return
 	}
 	o.notifyPersisted(full)

internal/services/gateway/ws_hub.go

@@ -235,8 +235,11 @@ func (h *hub) streamChat(ctx context.Context, payload any) {
 	// The Web main session is the owner's private conversation (JWT = owner), so
 	// it binds the full-access env: memory read+write, unchanged behavior.
 	msgs := userChatMessages(req.Text, req.Image)
+	// Thread the client's deviceID into the orchestrator via ctx so both the
+	// persisted user turn and the assistant reply are tagged (design/16 §4.5).
+	ctx = withDeviceID(ctx, req.DeviceID)
 	if h.orchestrator != nil {
-		_ = h.orchestrator.Submit(context.Background(), req.SessionID, msgs, loop.OwnerEnv())
+		_ = h.orchestrator.Submit(ctx, req.SessionID, msgs, loop.OwnerEnv())
 		return
 	}
 	_, _ = h.runTurn(ctx, req.SessionID, msgs, loop.OwnerEnv())
@@ -305,6 +308,10 @@ type chatStreamRequest struct {
 	SessionID string `json:"sessionId"`
 	Text      string `json:"text"`
 	Image     string `json:"image,omitempty"`
+	// DeviceID is the client-produced identifier of the sending browser/device
+	// (design/16 §4.5), e.g. "web:chrome:a1b2c3"; it is optional and persisted
+	// alongside the message so the agent knows which end the owner is chatting from.
+	DeviceID string `json:"deviceId,omitempty"`
 }
 
 // handleWS upgrades /ws/chat after authenticating the JWT from the query token or
@@ -432,11 +439,13 @@ func (c *wsConn) enqueueJSON(ev wsEvent) {
 }
 
 // publishChatStream publishes a ws.chat streaming trigger (REST stream mode).
-func (s *Server) publishChatStream(ctx context.Context, sessionID, text, image string) {
+// deviceID is the sending browser/device id carried on the payload so the ws.chat
+// consumer can tag the persisted turn (design/16 §4.5).
+func (s *Server) publishChatStream(ctx context.Context, sessionID, text, image, deviceID string) {
 	if s.bus == nil {
 		return
 	}
-	_ = s.bus.Publish(ctx, wsChatSubject, map[string]any{"sessionId": sessionID, "text": text, "image": image})
+	_ = s.bus.Publish(ctx, wsChatSubject, map[string]any{"sessionId": sessionID, "text": text, "image": image, "deviceId": deviceID})
 }
 
 // wsToken extracts the JWT from the ?token= query or the Authorization header.