更新

backend/main.py

@@ -20,7 +20,7 @@ from settings import CORS_ORIGINS, SERVE_WEB, STATIC_DIR
 from help_pages import serve_credential_tool
 from web_static import mount_frontend
 from pydantic import BaseModel, Field
-from sqlalchemy import select, update, delete, text, func, case
+from sqlalchemy import select, update, delete, text, func, case, or_, cast, String
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from models.database import engine, Base, get_db, AsyncSessionLocal
@@ -1080,42 +1080,91 @@ async def get_accounts(
       支持 q（昵称/抖音ID/手机号/账号ID 搜索）与 status 筛选。
       Cookie 解析等重逻辑只对当前页执行。
     """
-    result = await db.execute(accounts_for_user(user))
-    accounts = result.scalars().all()
-    # 更新内存中的运行状态与数据库同步，以防异常断开
-    for acc in accounts:
+    if page is None:
+        result = await db.execute(accounts_for_user(user))
+        accounts = result.scalars().all()
+        # 兼容旧的全量接口行为。
+        for acc in accounts:
+            is_running = manager.is_running(acc.id)
+            if is_running and acc.status == "offline":
+                acc.status = "online"
+            elif not is_running and acc.status in ("online", "logging_in", "starting"):
+                acc.status = "offline"
+        return [_build_account_response(acc) for acc in accounts]
+
+    keyword = (q or "").strip().lower()
+    status_filter = (status or "").strip()
+    stmt = accounts_for_user(user)
+    running_account_ids = [
+        int(account_id)
+        for account_id, worker in list(manager.workers.items())
+        if worker and worker.is_running
+    ]
+    runtime_running = Account.id.in_(running_account_ids)
+    effective_status = case(
+        (
+            runtime_running & (Account.status == "offline"),
+            "online",
+        ),
+        (
+            (~runtime_running)
+            & Account.status.in_(("online", "logging_in", "starting")),
+            "offline",
+        ),
+        else_=Account.status,
+    )
+
+    if keyword:
+        like_value = f"%{keyword}%"
+        search_conditions = [
+            func.lower(Account.username).like(like_value),
+            func.lower(Account.douyin_uid).like(like_value),
+            func.lower(Account.phone).like(like_value),
+            func.lower(Account.user_agent).like(like_value),
+            cast(Account.id, String).like(like_value),
+        ]
+        matching_profiles = [
+            profile
+            for profile in list_device_profiles()
+            if keyword in str(profile.get("label") or "").lower()
+            or keyword in str(profile.get("platform") or "").lower()
+        ]
+        if matching_profiles:
+            matching_uas = [profile["user_agent"] for profile in matching_profiles]
+            search_conditions.append(Account.user_agent.in_(matching_uas))
+            if any(profile.get("id") == "chrome_win120" for profile in matching_profiles):
+                search_conditions.append(Account.user_agent.is_(None))
+        stmt = stmt.where(or_(*search_conditions))
+
+    if status_filter and status_filter != "all":
+        if status_filter == "quota_disabled":
+            stmt = stmt.where(Account.quota_disabled.is_(True))
+        else:
+            stmt = stmt.where(
+                Account.quota_disabled.is_not(True),
+                effective_status == status_filter,
+            )
+
+    total_result = await db.execute(
+        stmt.with_only_columns(func.count(Account.id)).order_by(None)
+    )
+    total = int(total_result.scalar_one() or 0)
+    result = await db.execute(
+        stmt.order_by(Account.id.asc())
+        .offset((page - 1) * page_size)
+        .limit(page_size)
+    )
+    items = result.scalars().all()
+
+    # Only reconcile the current page.  The old implementation hydrated every
+    # account including large Cookie/IM blobs on every refresh, which became
+    # visibly slow beyond a few hundred accounts.
+    for acc in items:
         is_running = manager.is_running(acc.id)
         if is_running and acc.status == "offline":
             acc.status = "online"
         elif not is_running and acc.status in ("online", "logging_in", "starting"):
             acc.status = "offline"
-
-    if page is None:
-        return [_build_account_response(acc) for acc in accounts]
-
-    keyword = (q or "").strip().lower()
-    status_filter = (status or "").strip()
-    filtered = [
-        acc
-        for acc in accounts
-        if _account_matches_keyword(acc, keyword)
-        and (
-            not status_filter
-            or status_filter == "all"
-            or (
-                status_filter == "quota_disabled"
-                and bool(acc.quota_disabled)
-            )
-            or (
-                status_filter != "quota_disabled"
-                and not acc.quota_disabled
-                and acc.status == status_filter
-            )
-        )
-    ]
-    total = len(filtered)
-    start = (page - 1) * page_size
-    items = filtered[start : start + page_size]
     return {
         "items": [_build_account_response(acc) for acc in items],
         "total": total,
@@ -1330,14 +1379,55 @@ async def update_account(
 
 @app.get("/api/reply-queues", response_model=ReplyQueueSummaryResponse)
 async def get_reply_queue_summaries(
+    account_ids: Optional[str] = None,
     db: AsyncSession = Depends(get_db),
     user: User = Depends(get_current_user),
 ):
-    """聚合当前用户可见账号的排队数量，供账号页低频轮询。"""
-    allowed_ids = await owned_account_ids(db, user)
+    """聚合可见账号的排队数量；账号页可限定为当前页账号。"""
+    requested_ids: list[int] | None = None
+    if account_ids is not None:
+        requested_ids = []
+        seen_ids: set[int] = set()
+        for raw in str(account_ids).split(","):
+            token = raw.strip()
+            if not token:
+                continue
+            try:
+                account_id = int(token)
+            except (TypeError, ValueError):
+                raise HTTPException(status_code=400, detail="账号编号格式错误")
+            if account_id > 0 and account_id not in seen_ids:
+                seen_ids.add(account_id)
+                requested_ids.append(account_id)
+        if len(requested_ids) > 100:
+            raise HTTPException(status_code=400, detail="单次最多查询 100 个账号的回复队列")
+
+    allowed_ids: set[int] | None
+    if requested_ids is None:
+        allowed_ids = await owned_account_ids(db, user)
+        worker_entries = list(manager.workers.items())
+    else:
+        if is_admin(user.role):
+            allowed_ids = set(requested_ids)
+        elif requested_ids:
+            owned_result = await db.execute(
+                select(Account.id).where(
+                    Account.owner_id == user.id,
+                    Account.id.in_(requested_ids),
+                )
+            )
+            allowed_ids = {int(row[0]) for row in owned_result.all()}
+        else:
+            allowed_ids = set()
+        worker_entries = [
+            (account_id, manager.workers.get(account_id))
+            for account_id in requested_ids
+            if account_id in allowed_ids and account_id in manager.workers
+        ]
+
     summaries: list[ReplyQueueSummaryItem] = []
     total_pending = 0
-    for account_id, worker in list(manager.workers.items()):
+    for account_id, worker in worker_entries:
         if allowed_ids is not None and account_id not in allowed_ids:
             continue
         service = worker._im_service if worker else None
@@ -1688,7 +1778,11 @@ async def validate_account_credential(
     account = await get_owned_account(db, user, account_id)
 
     cookie_data = _get_account_cookie_data(account)
-    assessment = await assess_account_credential(cookie_data, account.im_session_data)
+    assessment = await assess_account_credential(
+        cookie_data,
+        account.im_session_data,
+        startup_priority=True,
+    )
     return CredentialValidateResponse(**assessment)
 
 
@@ -1718,7 +1812,11 @@ async def _start_account_rpa_impl(
         return {"status": "running", "message": "RPA worker is already running."}
 
     cookie_data = _get_account_cookie_data(account)
-    assessment = await assess_account_credential(cookie_data, account.im_session_data)
+    assessment = await assess_account_credential(
+        cookie_data,
+        account.im_session_data,
+        startup_priority=True,
+    )
     login_mode = requested_login_mode or assessment["login_mode"]
     reset_performed = False
 

backend/rpa_engine/batch_start.py

@@ -18,6 +18,10 @@ StartHandler = Callable[[int], Awaitable[dict[str, Any]]]
 JobToken = tuple[str, int]
 
 
+class _StartPreparationTimeout(Exception):
+    """Internal marker for the queue's own per-account deadline."""
+
+
 def _configured_concurrency() -> int:
     try:
         return max(1, min(8, int(os.getenv("KEFU_BATCH_START_CONCURRENCY", "2"))))
@@ -25,6 +29,16 @@ def _configured_concurrency() -> int:
         return 2
 
 
+def _configured_timeout_seconds() -> float:
+    try:
+        value = float(os.getenv("KEFU_BATCH_START_TIMEOUT_SECONDS", "90"))
+    except (TypeError, ValueError):
+        return 90.0
+    if value <= 0:
+        return 0.0
+    return max(5.0, min(600.0, value))
+
+
 def _utc_now() -> str:
     return datetime.now(timezone.utc).isoformat()
 
@@ -55,10 +69,16 @@ class BatchStartQueue:
         handler: StartHandler,
         concurrency: int | None = None,
         max_batches: int = 100,
+        timeout_seconds: float | None = None,
     ) -> None:
         self._handler = handler
         self.concurrency = max(1, int(concurrency or _configured_concurrency()))
         self.max_batches = max(10, int(max_batches or 100))
+        self.timeout_seconds = (
+            _configured_timeout_seconds()
+            if timeout_seconds is None
+            else max(0.0, float(timeout_seconds or 0.0))
+        )
         self._queue: asyncio.Queue[JobToken] = asyncio.Queue()
         self._pending_jobs: dict[int, JobToken] = {}
         self._active_tasks: dict[int, tuple[JobToken, asyncio.Task]] = {}
@@ -157,7 +177,21 @@ class BatchStartQueue:
                     )
                     self._active_tasks[account_id] = (job_token, handler_task)
 
-                result = await handler_task
+                if self.timeout_seconds > 0:
+                    try:
+                        result = await asyncio.wait_for(
+                            handler_task,
+                            timeout=self.timeout_seconds,
+                        )
+                    except asyncio.TimeoutError as exc:
+                        # wait_for cancels its task only when this queue's
+                        # deadline expires.  Preserve a TimeoutError raised by
+                        # the handler itself as its real account failure.
+                        if handler_task.cancelled():
+                            raise _StartPreparationTimeout from exc
+                        raise
+                else:
+                    result = await handler_task
                 async with self._lock:
                     record = self._batches.get(batch_id)
                     if record:
@@ -171,6 +205,28 @@ class BatchStartQueue:
                                 elapsed_seconds=round(time.monotonic() - started_at, 3),
                             )
                         record.updated_at = _utc_now()
+            except _StartPreparationTimeout:
+                elapsed = round(time.monotonic() - started_at, 3)
+                logger.warning(
+                    "Batch start timed out account=%s worker=%s after %.1fs",
+                    account_id,
+                    worker_number,
+                    self.timeout_seconds,
+                )
+                async with self._lock:
+                    record = self._batches.get(batch_id)
+                    if record:
+                        item = record.items[account_id]
+                        if item.get("status") != "cancelled":
+                            item.update(
+                                status="failed",
+                                message=(
+                                    f"启动准备超过 {self.timeout_seconds:g} 秒，"
+                                    "已跳过并继续处理后续账号"
+                                ),
+                                elapsed_seconds=elapsed,
+                            )
+                        record.updated_at = _utc_now()
             except asyncio.CancelledError:
                 async with self._lock:
                     record = self._batches.get(batch_id)

backend/rpa_engine/credential.py

@@ -6,7 +6,6 @@ from typing import Optional
 
 from rpa_engine.douyin_im.auth import DouyinAuth
 from rpa_engine.douyin_im.frontier import ensure_frontier_ws
-from rpa_engine.douyin_im.http_client import DouyinImHttpClient
 from rpa_engine.douyin_im.session import DouyinImSession
 from utils.cookie_store import analyze_cookie
 
@@ -131,13 +130,26 @@ async def build_cookie_credential_detail(
 async def validate_im_session(
     session: DouyinImSession,
     _bypass_global_limit: bool = False,
+    *,
+    startup_priority: bool = False,
 ) -> tuple[bool, str]:
     if not _bypass_global_limit:
         from rpa_engine.douyin_im.traffic_control import get_traffic_controller
 
         controller = get_traffic_controller()
-        async with controller.background_slot(0, "credential validation"):
-            return await validate_im_session(session, _bypass_global_limit=True)
+        # Startup validation must not sit behind hundreds of recurring
+        # conversation polls.  It still shares the same global concurrency
+        # cap, so this changes ordering without increasing bandwidth usage.
+        async with controller.background_slot(
+            0,
+            "credential validation",
+            startup=startup_priority,
+        ):
+            return await validate_im_session(
+                session,
+                _bypass_global_limit=True,
+                startup_priority=startup_priority,
+            )
 
     if not session.can_direct_im():
         if not has_im_session_token(session):
@@ -155,17 +167,12 @@ async def validate_im_session(
         if not auth.is_sign_ready():
             return False, "缺少 IM 签名密钥（web_protect/keys），请用浏览器登录补全"
         session.my_uid = int(uid)
-        async with DouyinImHttpClient(session) as http:
-            await http.get_unread_count()
-            # 若已缓存到会话票据，优先校验其是否仍新鲜（最理想）。
-            if session.conv_meta:
-                ok, reason = await http.verify_messaging_capability(auth, session.my_uid)
-                if ok:
-                    return True, reason
-            # 没有缓存会话票据是首次登录的正常情况：会话 ticket 会在发送时即时
-            # 创建/获取（resolve_conversation_meta），因此只要 Cookie + sessionid +
-            # 签名密钥(web_protect/keys) + UID 齐全，就视为可 IM 直连托管，不必再开浏览器。
-            return True, "IM 凭证就绪（Cookie 与签名密钥齐全，可直连托管）"
+        # unread_count and ticket probes were previously issued here, but
+        # neither result changed the final decision: unread failures become
+        # zero and a stale/missing ticket is resolved lazily at send time.
+        # Keeping those probes doubled large-batch startup traffic without
+        # adding an authoritative validation signal.
+        return True, "IM 凭证就绪（Cookie 与签名密钥齐全，可直连托管）"
     except Exception as e:
         logger.warning(f"IM session validation failed: {e}")
         return False, f"IM 运行时验证失败: {e}"
@@ -174,6 +181,8 @@ async def validate_im_session(
 async def assess_account_credential(
     cookie_data: Optional[str],
     im_session_data: Optional[str] = None,
+    *,
+    startup_priority: bool = False,
 ) -> dict:
     cookie_info = analyze_cookie(cookie_data)
     result = {
@@ -212,7 +221,10 @@ async def assess_account_credential(
         result["should_reset"] = _should_reset_credentials(result)
         return result
 
-    im_ok, im_reason = await validate_im_session(session)
+    im_ok, im_reason = await validate_im_session(
+        session,
+        startup_priority=startup_priority,
+    )
     result["im_ready"] = im_ok
     if im_ok:
         result["can_skip_browser"] = True

backend/rpa_engine/douyin_im/http_client.py

@@ -737,7 +737,7 @@ class DouyinImHttpClient:
                     pass
         return total
 
-    async def get_conversations(self) -> list[dict]:
+    async def get_conversations(self, *, enrich_profiles: bool = True) -> list[dict]:
         """拉取会话列表，返回标准化会话"""
         payloads = [
             {"cursor": 0, "count": 50, "inbox_type": 0},
@@ -754,7 +754,12 @@ class DouyinImHttpClient:
             if data is None:
                 data = await self._request("GET", "/v1/conversation/list", body)
             if data is None:
-                continue
+                # Payload variants only help with schema compatibility.  They
+                # cannot repair a network outage, so stop after POST + GET
+                # both fail instead of occupying a scarce global slot for up
+                # to four more full request timeouts.
+                logger.warning("Conversation poll transport failed; skipping payload fallbacks")
+                break
 
             status_code = data.get("status_code") if isinstance(data, dict) else None
             error_text = ""
@@ -814,6 +819,9 @@ class DouyinImHttpClient:
         enriched: list[dict] = []
         for item in conversations:
             conv = enrich_conversation_item(item, my_uid)
+            if not enrich_profiles:
+                enriched.append(conv)
+                continue
             peer_uid = str(conv.get("peer_uid") or "")
             name = (conv.get("sender_name") or "").strip()
             avatar = str(conv.get("sender_avatar") or "").strip()

backend/rpa_engine/douyin_im/service.py

@@ -1,5 +1,6 @@
 import asyncio
 import logging
+import os
 import time
 from typing import Awaitable, Callable, Optional
 
@@ -26,6 +27,30 @@ LogFn = Callable[..., Awaitable[None]]
 ReceivedLogFn = Callable[..., Awaitable[None]]
 
 
+def _env_poll_seconds(name: str, default: float, minimum: float = 5.0) -> float:
+    try:
+        return max(minimum, float(os.getenv(name, str(default))))
+    except (TypeError, ValueError):
+        return default
+
+
+def _conversation_poll_timing(account_id: int, has_ws: bool) -> tuple[float, float]:
+    """Return the reconciliation interval and a stable per-account stagger.
+
+    WebSocket is the real-time receive path.  HTTP polling is only a safety
+    reconciliation when that path exists, so running it every 15 seconds for
+    hundreds of accounts wastes bandwidth and eventually starves new starts.
+    Accounts without WebSocket keep the original fast polling cadence.
+    """
+    interval = _env_poll_seconds(
+        "KEFU_WS_RECONCILE_INTERVAL_SECONDS" if has_ws else "KEFU_HTTP_POLL_INTERVAL_SECONDS",
+        120.0 if has_ws else 15.0,
+    )
+    spread_ms = max(1, int(interval * 1000))
+    stagger = ((int(account_id or 0) * 2654435761) % spread_ms) / 1000.0
+    return interval, stagger
+
+
 class DouyinImService:
     """抖音 IM 直连服务：WebSocket 实时监听 + HTTP 轮询 + 自动回复"""
 
@@ -734,11 +759,18 @@ class DouyinImService:
         controller = get_traffic_controller()
         async with controller.background_slot(self.account_id, "conversation poll"):
             async with DouyinImHttpClient(self.session, account_id=self.account_id) as http:
-                unread_total = await http.get_unread_count()
-                if unread_total:
-                    logger.info(f"IM unread total: {unread_total}")
-                conversations = await http.get_conversations()
-                await self._index_conversations(conversations)
+                conversations = await http.get_conversations(enrich_profiles=False)
+        # Profile enrichment may involve several slow third-party requests.
+        # Run it after releasing the conversation-list slot; each individual
+        # lookup re-enters the shared controller and yields fairly to startup
+        # validation and other accounts between profiles.
+        await self._index_conversations(conversations)
+        unread_total = sum(
+            max(0, int(item.get("unread_count") or 0))
+            for item in conversations
+        )
+        if unread_total:
+            logger.info(f"IM unread total: {unread_total}")
         # Message handling may wait in the global send lane.  Do not keep one
         # of the scarce background HTTP slots occupied while that happens.
         for conv in conversations:
@@ -811,8 +843,10 @@ class DouyinImService:
         )
         await self._ws_client.start()
 
+        initial_poll_succeeded = False
         try:
             await self._poll_conversations()
+            initial_poll_succeeded = True
         except Exception as e:
             logger.warning(f"Initial conversation poll failed: {e}")
             system_logger.record(
@@ -823,6 +857,34 @@ class DouyinImService:
                 account_id=self.account_id,
             )
 
+        ws_connected = bool(
+            self._ws_client and getattr(self._ws_client, "connected", False)
+        )
+        poll_interval, poll_stagger = _conversation_poll_timing(
+            self.account_id,
+            ws_connected,
+        )
+        loop = asyncio.get_running_loop()
+        if initial_poll_succeeded:
+            initial_retry_interval = poll_interval
+            initial_retry_stagger = poll_stagger
+        else:
+            # If the authoritative first poll failed, retry on the fast HTTP
+            # cadence even when WebSocket connected in the meantime.
+            initial_retry_interval, initial_retry_stagger = (
+                _conversation_poll_timing(self.account_id, False)
+            )
+        next_conversation_poll_at = (
+            loop.time() + initial_retry_interval + initial_retry_stagger
+        )
+        logger.info(
+            "Conversation reconciliation account=%s interval=%.1fs stagger=%.1fs ws=%s",
+            self.account_id,
+            poll_interval,
+            poll_stagger,
+            "yes" if ws_connected else "no",
+        )
+
         loop_count = 0
         while self._running:
             # The initial poll above is authoritative.  Sleep before the next
@@ -832,8 +894,39 @@ class DouyinImService:
                 break
             loop_count += 1
             try:
-                if loop_count % 3 == 0:
-                    await self._poll_conversations()
+                current_ws_connected = bool(
+                    self._ws_client
+                    and getattr(self._ws_client, "connected", False)
+                )
+                if current_ws_connected != ws_connected:
+                    ws_connected = current_ws_connected
+                    poll_interval, poll_stagger = _conversation_poll_timing(
+                        self.account_id,
+                        ws_connected,
+                    )
+                    candidate_poll_at = loop.time() + poll_interval + poll_stagger
+                    # Never postpone an already scheduled reconciliation.
+                    # In particular, reconnecting must preserve the earlier
+                    # fallback poll that covers messages missed while offline.
+                    next_conversation_poll_at = min(
+                        next_conversation_poll_at,
+                        candidate_poll_at,
+                    )
+                    logger.info(
+                        "Conversation reconciliation rescheduled account=%s "
+                        "interval=%.1fs ws=%s",
+                        self.account_id,
+                        poll_interval,
+                        "yes" if ws_connected else "no",
+                    )
+                if loop.time() >= next_conversation_poll_at:
+                    try:
+                        await self._poll_conversations()
+                    finally:
+                        # Advance on both success and failure.  Otherwise a
+                        # past deadline retries every five-second loop tick
+                        # during an outage and amplifies traffic.
+                        next_conversation_poll_at = loop.time() + poll_interval
                 if loop_count % 6 == 0:
                     logger.info(f"IM direct tick #{loop_count} account={self.account_id}")
                 # 关注欢迎语：约每 60s 检测一次新粉丝（独立于私信轮询，失败不影响主循环）

backend/rpa_engine/douyin_im/traffic_control.py

@@ -396,6 +396,15 @@ class TrafficController:
         self._background = asyncio.Semaphore(
             _env_int("KEFU_BACKGROUND_NETWORK_CONCURRENCY", 2)
         )
+        # Recurring polls can create hundreds of waiters when many accounts
+        # are online.  Admit at most one normal waiter to the semaphore at a
+        # time so startup validation can join near the front instead of being
+        # buried behind the entire polling backlog.  The shared semaphore is
+        # still the single bandwidth cap; startup work does not add extra
+        # network concurrency.
+        self._background_normal_admission = asyncio.Lock()
+        self._background_startup_clear = asyncio.Event()
+        self._background_startup_clear.set()
         self._browser = asyncio.Semaphore(
             _env_int("KEFU_BROWSER_START_CONCURRENCY", 1)
         )
@@ -410,12 +419,20 @@ class TrafficController:
         )
         self.background_waiting = 0
         self.background_active = 0
+        self.background_startup_waiting = 0
+        self.background_startup_active = 0
         self.browser_waiting = 0
         self.browser_active = 0
         self.media_proxy_active = 0
 
     @asynccontextmanager
-    async def background_slot(self, account_id: int = 0, description: str = "request"):
+    async def background_slot(
+        self,
+        account_id: int = 0,
+        description: str = "request",
+        *,
+        startup: bool = False,
+    ):
         current_task = asyncio.current_task()
         owner_task, depth = self._background_owner.get()
         if owner_task is current_task and depth > 0:
@@ -429,12 +446,29 @@ class TrafficController:
         started = asyncio.get_running_loop().time()
         self.background_waiting += 1
         try:
-            await self._background.acquire()
+            if startup:
+                self.background_startup_waiting += 1
+                self._background_startup_clear.clear()
+                try:
+                    await self._background.acquire()
+                finally:
+                    self.background_startup_waiting -= 1
+                    if self.background_startup_waiting == 0:
+                        self._background_startup_clear.set()
+            else:
+                # Only one recurring/background request may wait directly on
+                # the shared semaphore.  A later startup request therefore
+                # has at most one normal request ahead of it, not hundreds.
+                async with self._background_normal_admission:
+                    await self._background_startup_clear.wait()
+                    await self._background.acquire()
         except BaseException:
             self.background_waiting -= 1
             raise
         self.background_waiting -= 1
         self.background_active += 1
+        if startup:
+            self.background_startup_active += 1
         token = self._background_owner.set((current_task, 1))
         waited = asyncio.get_running_loop().time() - started
         if waited >= 1.0:
@@ -448,6 +482,8 @@ class TrafficController:
             yield
         finally:
             self._background_owner.reset(token)
+            if startup:
+                self.background_startup_active -= 1
             self.background_active -= 1
             self._background.release()
 
@@ -492,6 +528,8 @@ class TrafficController:
             "background": {
                 "active": self.background_active,
                 "waiting": self.background_waiting,
+                "startup_active": self.background_startup_active,
+                "startup_waiting": self.background_startup_waiting,
             },
             "browser": {
                 "active": self.browser_active,

backend/rpa_engine/douyin_im/ws_client.py

@@ -27,6 +27,7 @@ class DouyinImWsClient:
         self.on_message = on_message
         self.account_id = account_id
         self._running = False
+        self.connected = False
         self._task: Optional[asyncio.Task] = None
         self._loop: Optional[asyncio.AbstractEventLoop] = None
         self._ws_app: Optional[WebSocketApp] = None
@@ -50,6 +51,7 @@ class DouyinImWsClient:
 
     async def stop(self):
         self._running = False
+        self.connected = False
         with self._ws_lock:
             if self._ws_app:
                 try:
@@ -150,6 +152,7 @@ class DouyinImWsClient:
             return
 
         def on_open(_ws):
+            self.connected = True
             logger.info("IM WebSocket connected")
             system_logger.record(
                 "实时接收通道已连接",
@@ -174,6 +177,7 @@ class DouyinImWsClient:
                 )
 
         def on_close(_ws, code, msg):
+            self.connected = False
             logger.info(f"IM WebSocket closed: code={code}, msg={msg}")
             if self._running:
                 system_logger.record(
@@ -206,6 +210,7 @@ class DouyinImWsClient:
         try:
             ws_app.run_forever(origin="https://www.douyin.com", ping_interval=20, ping_timeout=10)
         finally:
+            self.connected = False
             with self._ws_lock:
                 if self._ws_app is ws_app:
                     self._ws_app = None

backend/tests/test_account_pagination.py

@@ -0,0 +1,152 @@
+from __future__ import annotations
+
+import os
+import sys
+import unittest
+from pathlib import Path
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, patch
+
+from sqlalchemy.ext.asyncio import AsyncSession, create_async_engine
+from sqlalchemy.orm import sessionmaker
+
+
+BACKEND_DIR = Path(__file__).resolve().parents[1]
+os.environ["KEFU_DB_TYPE"] = "sqlite"
+os.environ["KEFU_DATABASE_URL"] = ""
+os.environ["KEFU_DB_PATH"] = str(BACKEND_DIR / "kefu.db")
+if str(BACKEND_DIR) not in sys.path:
+    sys.path.insert(0, str(BACKEND_DIR))
+
+import main
+from models.database import Base
+from models.models import Account
+
+
+class _CountResult:
+    def __init__(self, count: int):
+        self.count = count
+
+    def scalar_one(self):
+        return self.count
+
+
+class _RowsResult:
+    def __init__(self, rows):
+        self.rows = list(rows)
+
+    def scalars(self):
+        return self
+
+    def all(self):
+        return list(self.rows)
+
+
+class AccountPaginationTests(unittest.IsolatedAsyncioTestCase):
+    async def test_paginated_list_counts_then_loads_only_current_page(self):
+        page_rows = [
+            SimpleNamespace(id=10, status="offline"),
+            SimpleNamespace(id=11, status="online"),
+        ]
+        db = SimpleNamespace(
+            execute=AsyncMock(
+                side_effect=[
+                    _CountResult(392),
+                    _RowsResult(page_rows),
+                ]
+            )
+        )
+
+        with (
+            patch.object(main.manager, "is_running", side_effect=[False, True]),
+            patch.object(
+                main,
+                "_build_account_response",
+                side_effect=lambda account: {"id": account.id, "status": account.status},
+            ) as build_response,
+        ):
+            response = await main.get_accounts(
+                page=20,
+                page_size=20,
+                q=None,
+                status=None,
+                db=db,
+                user=SimpleNamespace(id=1, role="admin"),
+            )
+
+        self.assertEqual(db.execute.await_count, 2)
+        self.assertEqual(response["total"], 392)
+        self.assertEqual(response["page"], 20)
+        self.assertEqual(response["page_size"], 20)
+        self.assertEqual([item["id"] for item in response["items"]], [10, 11])
+        self.assertEqual(build_response.call_count, 2)
+
+        count_sql = str(db.execute.await_args_list[0].args[0]).upper()
+        page_sql = str(db.execute.await_args_list[1].args[0]).upper()
+        self.assertIn("COUNT", count_sql)
+        self.assertNotIn(" LIMIT ", count_sql)
+        self.assertIn(" LIMIT ", page_sql)
+        self.assertIn(" OFFSET ", page_sql)
+
+    async def test_status_filter_uses_effective_runtime_worker_state(self):
+        engine = create_async_engine("sqlite+aiosqlite:///:memory:")
+        async with engine.begin() as connection:
+            await connection.run_sync(Base.metadata.create_all)
+        session_factory = sessionmaker(
+            engine,
+            class_=AsyncSession,
+            expire_on_commit=False,
+        )
+        original_workers = main.manager.workers
+        main.manager.workers = {
+            1001: SimpleNamespace(is_running=True),
+            1002: SimpleNamespace(is_running=False),
+        }
+        try:
+            async with session_factory() as db:
+                db.add_all(
+                    [
+                        Account(id=1001, status="offline"),
+                        Account(id=1002, status="online"),
+                    ]
+                )
+                await db.commit()
+
+                with patch.object(
+                    main,
+                    "_build_account_response",
+                    side_effect=lambda account: {
+                        "id": account.id,
+                        "status": account.status,
+                    },
+                ):
+                    online = await main.get_accounts(
+                        page=1,
+                        page_size=20,
+                        q=None,
+                        status="online",
+                        db=db,
+                        user=SimpleNamespace(id=1, role="admin"),
+                    )
+                    await db.rollback()
+                    db.expire_all()
+                    offline = await main.get_accounts(
+                        page=1,
+                        page_size=20,
+                        q=None,
+                        status="offline",
+                        db=db,
+                        user=SimpleNamespace(id=1, role="admin"),
+                    )
+
+            self.assertEqual(online["total"], 1)
+            self.assertEqual(online["items"], [{"id": 1001, "status": "online"}])
+            self.assertEqual(offline["total"], 1)
+            self.assertEqual(offline["items"], [{"id": 1002, "status": "offline"}])
+        finally:
+            main.manager.workers = original_workers
+            await engine.dispose()
+
+
+if __name__ == "__main__":
+    unittest.main()

backend/tests/test_batch_start_queue.py

@@ -17,8 +17,18 @@ from rpa_engine import batch_start as batch_start_module
 
 
 class BatchStartQueueTests(unittest.IsolatedAsyncioTestCase):
-    def _make_queue(self, handler, *, concurrency: int = 2) -> BatchStartQueue:
-        queue = BatchStartQueue(handler, concurrency=concurrency)
+    def _make_queue(
+        self,
+        handler,
+        *,
+        concurrency: int = 2,
+        timeout_seconds: float | None = None,
+    ) -> BatchStartQueue:
+        queue = BatchStartQueue(
+            handler,
+            concurrency=concurrency,
+            timeout_seconds=timeout_seconds,
+        )
         self.addAsyncCleanup(queue.stop)
         return queue
 
@@ -168,6 +178,54 @@ class BatchStartQueueTests(unittest.IsolatedAsyncioTestCase):
         self.assertEqual(by_account[32]["status"], "submitted")
         self.assertEqual(by_account[33]["status"], "submitted")
 
+    async def test_two_timeouts_release_both_workers_for_following_accounts(self):
+        never_release = asyncio.Event()
+        calls: list[int] = []
+
+        async def handler(account_id: int) -> dict:
+            calls.append(account_id)
+            if account_id in (71, 72):
+                await never_release.wait()
+            return {"message": f"started-{account_id}"}
+
+        queue = self._make_queue(
+            handler,
+            concurrency=2,
+            timeout_seconds=0.02,
+        )
+        with patch.object(batch_start_module.logger, "warning"):
+            submitted = await queue.submit([71, 72, 73, 74])
+            completed = await self._wait_for_complete(
+                queue,
+                submitted["batch_id"],
+            )
+
+        self.assertEqual(calls, [71, 72, 73, 74])
+        self.assertEqual(completed["failed_count"], 2)
+        self.assertEqual(completed["submitted_count"], 2)
+        by_account = {item["account_id"]: item for item in completed["items"]}
+        self.assertIn("已跳过并继续处理后续账号", by_account[71]["message"])
+        self.assertIn("已跳过并继续处理后续账号", by_account[72]["message"])
+        self.assertEqual(by_account[73]["status"], "submitted")
+        self.assertEqual(by_account[74]["status"], "submitted")
+
+    async def test_handler_timeout_error_keeps_its_original_detail(self):
+        async def handler(_account_id: int) -> dict:
+            raise asyncio.TimeoutError("upstream request timed out")
+
+        queue = self._make_queue(
+            handler,
+            concurrency=1,
+            timeout_seconds=10,
+        )
+        with patch.object(batch_start_module.logger, "exception"):
+            submitted = await queue.submit([75])
+            completed = await self._wait_for_complete(queue, submitted["batch_id"])
+
+        item = completed["items"][0]
+        self.assertEqual(item["status"], "failed")
+        self.assertEqual(item["message"], "upstream request timed out")
+
     async def test_failed_account_can_be_submitted_again(self):
         attempts = 0
 

backend/tests/test_conversation_poll_bandwidth.py

@@ -3,8 +3,9 @@ from __future__ import annotations
 import os
 import sys
 import unittest
+from contextlib import asynccontextmanager
 from pathlib import Path
-from unittest.mock import AsyncMock
+from unittest.mock import AsyncMock, patch
 
 
 BACKEND_DIR = Path(__file__).resolve().parents[1]
@@ -16,6 +17,8 @@ if str(BACKEND_DIR) not in sys.path:
 
 from rpa_engine.douyin_im.http_client import DouyinImHttpClient
 from rpa_engine.douyin_im.session import DouyinImSession
+from rpa_engine.douyin_im.service import DouyinImService, _conversation_poll_timing
+from rpa_engine.douyin_im import service as service_module
 
 
 class ConversationPollBandwidthTests(unittest.IsolatedAsyncioTestCase):
@@ -75,6 +78,71 @@ class ConversationPollBandwidthTests(unittest.IsolatedAsyncioTestCase):
             ["POST", "GET"],
         )
 
+    async def test_transport_outage_stops_after_one_post_and_get_pair(self):
+        client = self._make_client()
+        client._request = AsyncMock(return_value=None)
+
+        with self.assertLogs("douyin_im.http", level="WARNING"):
+            self.assertEqual(await client.get_conversations(), [])
+
+        self.assertEqual(client._request.await_count, 2)
+        self.assertEqual(
+            [call.args[0] for call in client._request.await_args_list],
+            ["POST", "GET"],
+        )
+
+    def test_websocket_reconciliation_is_slow_and_http_fallback_stays_fast(self):
+        with patch.dict(
+            os.environ,
+            {
+                "KEFU_WS_RECONCILE_INTERVAL_SECONDS": "120",
+                "KEFU_HTTP_POLL_INTERVAL_SECONDS": "15",
+            },
+        ):
+            ws_interval, ws_stagger = _conversation_poll_timing(123, True)
+            http_interval, http_stagger = _conversation_poll_timing(123, False)
+
+        self.assertEqual(ws_interval, 120)
+        self.assertEqual(http_interval, 15)
+        self.assertGreaterEqual(ws_stagger, 0)
+        self.assertLess(ws_stagger, ws_interval)
+        self.assertGreaterEqual(http_stagger, 0)
+        self.assertLess(http_stagger, http_interval)
+
+    async def test_service_poll_uses_one_conversation_request_without_unread_probe(self):
+        class _Controller:
+            @asynccontextmanager
+            async def background_slot(self, *_args, **_kwargs):
+                yield
+
+        class _HttpClient:
+            def __init__(self):
+                self.get_conversations = AsyncMock(return_value=[])
+
+            async def __aenter__(self):
+                return self
+
+            async def __aexit__(self, *_args):
+                return False
+
+        http = _HttpClient()
+        service = DouyinImService(
+            session=DouyinImSession(cookies={"sessionid": "test"}, my_uid=10001),
+            match_reply=AsyncMock(return_value=None),
+            log_fn=AsyncMock(),
+            account_id=9,
+        )
+        service._index_conversations = AsyncMock()
+
+        with (
+            patch.object(service_module, "get_traffic_controller", return_value=_Controller()),
+            patch.object(service_module, "DouyinImHttpClient", return_value=http),
+        ):
+            await service._poll_conversations()
+
+        http.get_conversations.assert_awaited_once_with(enrich_profiles=False)
+        service._index_conversations.assert_awaited_once_with([])
+
 
 if __name__ == "__main__":
     unittest.main()

backend/tests/test_reply_queue_api.py

@@ -84,6 +84,27 @@ class ReplyQueueApiTests(unittest.IsolatedAsyncioTestCase):
         self.assertEqual(response.total_pending, 1)
         self.assertEqual([item.account_id for item in response.items], [1])
 
+    async def test_summary_with_account_ids_only_scans_requested_page(self):
+        service_one = _FakeService(1, [_queue_item(1)])
+        service_two = _FakeService(2, [_queue_item(2, "job-2")])
+        service_one.get_reply_queue_snapshot = AsyncMock(return_value=service_one.items)
+        service_two.get_reply_queue_snapshot = AsyncMock(return_value=service_two.items)
+        main.manager.workers = {
+            1: SimpleNamespace(is_running=True, _im_service=service_one),
+            2: SimpleNamespace(is_running=True, _im_service=service_two),
+        }
+
+        response = await main.get_reply_queue_summaries(
+            account_ids="2",
+            db=object(),
+            user=SimpleNamespace(id=1, role="admin"),
+        )
+
+        service_one.get_reply_queue_snapshot.assert_not_awaited()
+        service_two.get_reply_queue_snapshot.assert_awaited_once()
+        self.assertEqual(response.total_pending, 1)
+        self.assertEqual([item.account_id for item in response.items], [2])
+
     async def test_offline_account_detail_returns_empty_snapshot(self):
         account = SimpleNamespace(id=1, reply_delay_seconds=0)
         with (

backend/tests/test_traffic_control.py

@@ -458,6 +458,70 @@ class BackgroundTrafficLimitTests(unittest.IsolatedAsyncioTestCase):
         self.assertEqual(len(tasks_seen), 3)
         self.assertTrue(all(task is tasks_seen[0] for task in tasks_seen))
 
+    async def test_startup_request_is_not_buried_behind_normal_backlog(self):
+        with patch.dict(
+            os.environ,
+            {"KEFU_BACKGROUND_NETWORK_CONCURRENCY": "1"},
+        ):
+            controller = TrafficController()
+        self.addAsyncCleanup(controller.stop)
+
+        entered: list[str] = []
+        releases = {
+            name: asyncio.Event()
+            for name in ("active", "normal-1", "normal-2", "startup")
+        }
+
+        async def request(name: str, *, startup: bool = False) -> None:
+            async with controller.background_slot(
+                1,
+                name,
+                startup=startup,
+            ):
+                entered.append(name)
+                await releases[name].wait()
+
+        active = asyncio.create_task(request("active"))
+        while entered != ["active"]:
+            await asyncio.sleep(0)
+
+        normal_one = asyncio.create_task(request("normal-1"))
+        normal_two = asyncio.create_task(request("normal-2"))
+        # Let one normal request reach the shared semaphore while the other is
+        # held at normal admission, then add the priority startup request.
+        await asyncio.sleep(0)
+        await asyncio.sleep(0)
+        startup = asyncio.create_task(request("startup", startup=True))
+        await asyncio.sleep(0)
+
+        releases["active"].set()
+        while len(entered) < 2:
+            await asyncio.sleep(0)
+        self.assertEqual(entered[:2], ["active", "normal-1"])
+
+        releases["normal-1"].set()
+        while len(entered) < 3:
+            await asyncio.sleep(0)
+        self.assertEqual(entered[:3], ["active", "normal-1", "startup"])
+
+        releases["startup"].set()
+        while len(entered) < 4:
+            await asyncio.sleep(0)
+        releases["normal-2"].set()
+        await asyncio.wait_for(
+            asyncio.gather(active, normal_one, normal_two, startup),
+            timeout=0.2,
+        )
+
+        self.assertEqual(
+            entered,
+            ["active", "normal-1", "startup", "normal-2"],
+        )
+        self.assertEqual(controller.background_active, 0)
+        self.assertEqual(controller.background_waiting, 0)
+        self.assertEqual(controller.background_startup_active, 0)
+        self.assertEqual(controller.background_startup_waiting, 0)
+
 
 class TrafficControllerLoopIsolationTests(unittest.TestCase):
     def test_get_traffic_controller_does_not_reuse_asyncio_primitives(self):

frontend/src/views/Accounts.vue

@@ -76,6 +76,13 @@ let batchStatusTimer = null
 let batchStatusRequestActive = false
 let batchStatusGeneration = 0
 const BATCH_STATUS_POLL_MS = 1500
+const BATCH_STATUS_MAX_POLL_MS = 5000
+const BATCH_STATUS_BACKOFF_STEP_MS = 750
+let batchStatusPollDelayMs = BATCH_STATUS_POLL_MS
+let batchStatusLastFinished = null
+let batchStatusLastTotal = null
+let batchStatusLastProcessing = null
+let batchStatusLastQueued = null
 const selectedIds = ref([])
 const addVisible = ref(false)
 const addSaving = ref(false)
@@ -711,9 +718,18 @@ const applyQueueSnapshot = (data, accountId) => {
 
 const fetchReplyQueueSummaries = async ({ silent = true } = {}) => {
   if (queueSummaryLoading.value) return
+  const accountIds = accounts.value
+    .map((account) => Number(account?.id))
+    .filter((accountId) => Number.isInteger(accountId) && accountId > 0)
+  if (!accountIds.length) {
+    replyQueueSummaries.value = {}
+    return
+  }
   queueSummaryLoading.value = true
   try {
-    const res = await api.get('/reply-queues')
+    const res = await api.get('/reply-queues', {
+      params: { account_ids: accountIds.join(',') }
+    })
     const rows = Array.isArray(res.data?.items) ? res.data.items : []
     const next = {}
     for (const row of rows) {
@@ -1152,6 +1168,11 @@ const stopBatchStatusPolling = () => {
     batchStatusTimer = null
   }
   batchStatusRequestActive = false
+  batchStatusPollDelayMs = BATCH_STATUS_POLL_MS
+  batchStatusLastFinished = null
+  batchStatusLastTotal = null
+  batchStatusLastProcessing = null
+  batchStatusLastQueued = null
 }
 
 const finishBatchStart = async (snapshot) => {
@@ -1181,6 +1202,7 @@ const finishBatchStart = async (snapshot) => {
   }
   await fetchAccounts()
   batchStarting.value = false
+  startReplyQueueSummaryPolling()
 }
 
 const pollBatchStartStatus = (batchId, initialSnapshot = null) => {
@@ -1196,11 +1218,31 @@ const pollBatchStartStatus = (batchId, initialSnapshot = null) => {
       Math.max(0, Number(snapshot?.failed_count) || 0) +
       Math.max(0, Number(snapshot?.skipped_count) || 0) +
       Math.max(0, Number(snapshot?.cancelled_count) || 0)
-    message.loading({
-      content: `账号启动队列处理中：${Math.min(finished, total)}/${total}`,
-      key: 'batch_start',
-      duration: 0
-    })
+    const processing = Math.max(0, Number(snapshot?.processing_count) || 0)
+    const queued = Math.max(0, Number(snapshot?.queued_count) || 0)
+    const visibleFinished = Math.min(finished, total)
+    const progressChanged =
+      visibleFinished !== batchStatusLastFinished ||
+      total !== batchStatusLastTotal ||
+      processing !== batchStatusLastProcessing ||
+      queued !== batchStatusLastQueued
+    if (progressChanged) {
+      batchStatusLastFinished = visibleFinished
+      batchStatusLastTotal = total
+      batchStatusLastProcessing = processing
+      batchStatusLastQueued = queued
+      batchStatusPollDelayMs = BATCH_STATUS_POLL_MS
+      message.loading({
+        content: `账号启动队列处理中：${visibleFinished}/${total}（正在处理 ${processing}，等待 ${queued}，系统正错峰启动）`,
+        key: 'batch_start',
+        duration: 0
+      })
+    } else {
+      batchStatusPollDelayMs = Math.min(
+        BATCH_STATUS_MAX_POLL_MS,
+        batchStatusPollDelayMs + BATCH_STATUS_BACKOFF_STEP_MS
+      )
+    }
     if (snapshot?.complete) {
       await finishBatchStart(snapshot)
       return true
@@ -1230,12 +1272,13 @@ const pollBatchStartStatus = (batchId, initialSnapshot = null) => {
         duration: 5
       })
       await fetchAccounts()
+      startReplyQueueSummaryPolling()
       return
     } finally {
       if (generation === batchStatusGeneration) batchStatusRequestActive = false
     }
     if (generation === batchStatusGeneration && activeStartBatchId.value === batchId) {
-      batchStatusTimer = setTimeout(poll, BATCH_STATUS_POLL_MS)
+      batchStatusTimer = setTimeout(poll, batchStatusPollDelayMs)
     }
   }
 
@@ -1245,7 +1288,7 @@ const pollBatchStartStatus = (batchId, initialSnapshot = null) => {
       generation === batchStatusGeneration &&
       activeStartBatchId.value === batchId
     ) {
-      batchStatusTimer = setTimeout(poll, BATCH_STATUS_POLL_MS)
+      batchStatusTimer = setTimeout(poll, batchStatusPollDelayMs)
     }
   })
 }
@@ -1254,6 +1297,7 @@ const pollBatchStartStatus = (batchId, initialSnapshot = null) => {
 const runBatchStart = async ({ accountIds = [], allAccounts = false }) => {
   if (batchStarting.value) return
   batchStarting.value = true
+  stopReplyQueueSummaryPolling()
   stopBatchStatusPolling()
   const submitGeneration = batchStatusGeneration
   message.loading({ content: '正在提交账号启动队列...', key: 'batch_start', duration: 0 })
@@ -1275,6 +1319,7 @@ const runBatchStart = async ({ accountIds = [], allAccounts = false }) => {
     if (submitGeneration !== batchStatusGeneration) return
     batchStarting.value = false
     activeStartBatchId.value = null
+    startReplyQueueSummaryPolling()
     message.error({
       content: error.response?.data?.detail || error.message || '提交批量启动失败',
       key: 'batch_start',