feat: IM平台列 + deviceID标识 + 会话持久化完善
CI / Backend (build / vet / test / cross-compile) (push) Has been cancelled
CI / Frontend (tsc + vite build) (push) Has been cancelled

- 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)
This commit is contained in:
Aska committed 2026-09-07 04:51:41 +08:00
1 parent 1bf60c1ae4
commit 37e98ec584
26 files changed
+828 -116

No files matched your search

+6 -1
View File
@@ -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,
}
}
@@ -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)
+5 -2
View File
@@ -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"))
+17 -12
View File
@@ -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 {
@@ -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.
@@ -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)
+15 -13
View File
@@ -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)
+12 -3
View File
@@ -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.