管理员智能体/技能管理 + 跨标签登录同步 + 上游响应异常重试

- 「设置和更多」新增「智能体管理」「技能管理」入口，与定时任务管理同级；
  独立的 AdminAgentsPage/AdminSkillsPage 复用 AgentCard/SkillRow，
  管理员可查看并编辑/删除所有用户的智能体与技能。
- 后端 /api/agents、/api/skills 增加 ?admin=true 越权列表；agents 端
  放宽 _get_editable_or_raise 让管理员可编辑/删除任意智能体；新增
  list_all/update_any/delete_any（agents）与 list_all（skills）。
- 新增 AuthSyncWatcher：监听 localStorage["deerflow.auth"] 的 storage
  事件，user_id 变化时自动 reload，修复多标签切换登录后老页面点击
  「新对话」偶发 404 的问题。
- LLMErrorHandlingMiddleware 将 bad_response_status_code / JSON
  decode 等上游网关乱码识别为可重试的 upstream 类故障。
- 侧边栏「任务管理」改名为「定时任务」。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

offline-backend-20260512/backend/packages/harness/deerflow/agents/middlewares/llm_error_handling_middleware.py

@@ -61,6 +61,21 @@ _AUTH_PATTERNS = (
     "无权",
     "未授权",
 )
+# Upstream model gateway returned a malformed payload (typically a JSON decode
+# error wrapped as `bad_response_status_code`, or a truncated/garbled inference
+# response). These are almost always transient inference-side issues and safe
+# to retry.
+_UPSTREAM_GARBAGE_PATTERNS = (
+    "bad_response_status_code",
+    "bad response status",
+    "expecting ',' delimiter",
+    "expecting value",
+    "expecting property name",
+    "unexpected character",
+    "unterminated string",
+    "extra data",
+    "jsondecodeerror",
+)
 
 
 class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
@@ -139,9 +154,10 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
         detail = _extract_error_detail(exc)
         lowered = detail.lower()
         error_code = _extract_error_code(exc)
+        error_code_lower = str(error_code).lower() if error_code is not None else ""
         status_code = _extract_status_code(exc)
 
-        if _matches_any(lowered, _QUOTA_PATTERNS) or _matches_any(str(error_code).lower(), _QUOTA_PATTERNS):
+        if _matches_any(lowered, _QUOTA_PATTERNS) or _matches_any(error_code_lower, _QUOTA_PATTERNS):
             return False, "quota"
         if _matches_any(lowered, _AUTH_PATTERNS):
             return False, "auth"
@@ -159,6 +175,11 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
             return True, "transient"
         if _matches_any(lowered, _BUSY_PATTERNS):
             return True, "busy"
+        # Treat upstream gateway garbage (malformed JSON, truncated responses)
+        # as a retriable transient — the deterministic char-position errors we
+        # see from vLLM/proxy layers usually clear on a re-roll.
+        if _matches_any(lowered, _UPSTREAM_GARBAGE_PATTERNS) or _matches_any(error_code_lower, _UPSTREAM_GARBAGE_PATTERNS):
+            return True, "upstream"
 
         return False, "generic"
 
@@ -171,21 +192,34 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
 
     def _build_retry_message(self, attempt: int, wait_ms: int, reason: str) -> str:
         seconds = max(1, round(wait_ms / 1000))
-        reason_text = "服务繁忙" if reason == "busy" else "网络/连接异常"
+        if reason == "busy":
+            reason_text = "服务繁忙"
+        elif reason == "upstream":
+            reason_text = "上游响应异常"
+        else:
+            reason_text = "网络/连接异常"
         return f"大模型因{reason_text}调用失败，正在第 {attempt}/{self.retry_max_attempts} 次重试，{seconds} 秒后继续…"
 
     def _build_circuit_breaker_message(self) -> str:
         return "大模型因连续多次调用失败已被熔断保护，请稍候再试。"
 
-    def _build_user_message(self, exc: BaseException, reason: str) -> str:
-        detail = _extract_error_detail(exc)
+    def _build_user_message(self, reason: str) -> str:
         if reason == "quota":
             return "大模型因账户额度不足、账单异常或使用受限而拒绝请求，请检查模型账户后再试。"
         if reason == "auth":
             return "大模型因鉴权失败或无访问权限而拒绝请求,请检查模型的 API Key 与权限配置后再试。"
         if reason in {"busy", "transient"}:
             return "大模型因服务繁忙或网络异常，多次重试后仍未恢复,请稍候再继续。"
-        return f"大模型因「{detail}」原因调用失败。"
+        if reason == "upstream":
+            return "大模型当前响应异常（上游模型或网关临时故障），多次重试后仍未恢复，请稍后再试或更换模型。"
+        # NOTE: We intentionally do NOT embed the raw exception detail into the
+        # user-facing message. Raw `Error code: 400 - {...}` strings — especially
+        # Python repr-style dict literals — get persisted as AI messages and then
+        # re-fed to the model on the next turn, where their unescaped quotes /
+        # braces can corrupt the upstream JSON payload and cause deterministic
+        # JSONDecodeError loops. Keep the user message clean; full detail is
+        # already in the backend log via `logger.warning(..., exc_info=exc)`.
+        return "大模型本次调用未能成功完成，请稍后再试或更换模型。"
 
     def _emit_retry_event(self, attempt: int, wait_ms: int, reason: str) -> None:
         try:
@@ -249,7 +283,7 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
                 )
                 if retriable:
                     self._record_failure()
-                return AIMessage(content=self._build_user_message(exc, reason))
+                return AIMessage(content=self._build_user_message(reason))
 
     @override
     async def awrap_model_call(
@@ -295,7 +329,7 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
                 )
                 if retriable:
                     self._record_failure()
-                return AIMessage(content=self._build_user_message(exc, reason))
+                return AIMessage(content=self._build_user_message(reason))
 
 
 def _matches_any(detail: str, patterns: tuple[str, ...]) -> bool:

offline-backend-20260512/backend/packages/harness/deerflow/persistence/agents/base.py

@@ -90,3 +90,30 @@ class AgentStore(ABC):
         already verified the admin-configured private-square password.
         """
         raise NotImplementedError
+
+    @abstractmethod
+    async def list_all(self) -> list[dict[str, Any]]:
+        """Return every agent regardless of ownership/visibility.
+
+        Caller is responsible for authorization — typically the caller has
+        already verified ``system_role == "admin"``.
+        """
+        raise NotImplementedError
+
+    @abstractmethod
+    async def update_any(self, agent_id: str, data: dict[str, Any]) -> dict[str, Any] | None:
+        """Update any agent row by id, regardless of ownership.
+
+        Caller is responsible for authorization (admin only). Returns ``None``
+        if the agent does not exist.
+        """
+        raise NotImplementedError
+
+    @abstractmethod
+    async def delete_any(self, agent_id: str) -> bool:
+        """Delete any agent row by id, regardless of ownership.
+
+        Caller is responsible for authorization (admin only). Returns
+        ``False`` if the agent does not exist.
+        """
+        raise NotImplementedError

offline-backend-20260512/backend/packages/harness/deerflow/persistence/agents/memory.py

@@ -138,3 +138,29 @@ class MemoryAgentStore(AgentStore):
         rows = [self._agents[aid] for aid in agent_ids if aid in self._agents and self._is_visible(self._agents[aid], user_id)]
         rows.sort(key=lambda a: order_map.get(a["id"], 0))
         return [_copy(a) for a in rows]
+
+    async def list_private(self) -> list[dict[str, Any]]:
+        rows = [_copy(a) for a in self._agents.values() if bool(a.get("is_private"))]
+        rows.sort(key=lambda a: a.get("created_at") or "")
+        return rows
+
+    async def list_all(self) -> list[dict[str, Any]]:
+        rows = [_copy(a) for a in self._agents.values()]
+        rows.sort(key=lambda a: a.get("created_at") or "")
+        return rows
+
+    async def update_any(self, agent_id: str, data: dict[str, Any]) -> dict[str, Any] | None:
+        row = self._agents.get(agent_id)
+        if row is None:
+            return None
+        for key in ("name", "description", "published", "is_private"):
+            if key in data:
+                row[key] = data[key]
+        row["updated_at"] = _now()
+        return _copy(row)
+
+    async def delete_any(self, agent_id: str) -> bool:
+        if agent_id not in self._agents:
+            return False
+        self._agents.pop(agent_id, None)
+        return True

offline-backend-20260512/backend/packages/harness/deerflow/persistence/agents/sql.py

@@ -202,3 +202,31 @@ class AgentRepository(AgentStore):
         async with self._sf() as session:
             result = await session.execute(stmt)
             return [_row_to_dict(row) for row in result.scalars()]
+
+    async def list_all(self) -> list[dict[str, Any]]:
+        stmt = select(AgentRow).order_by(AgentRow.created_at.asc())
+        async with self._sf() as session:
+            result = await session.execute(stmt)
+            return [_row_to_dict(row) for row in result.scalars()]
+
+    async def update_any(self, agent_id: str, data: dict[str, Any]) -> dict[str, Any] | None:
+        async with self._sf() as session:
+            row = await session.get(AgentRow, agent_id)
+            if row is None:
+                return None
+            for key in ("name", "description", "published", "is_private"):
+                if key in data:
+                    setattr(row, key, data[key])
+            row.updated_at = datetime.now(UTC)
+            await session.commit()
+            await session.refresh(row)
+            return _row_to_dict(row)
+
+    async def delete_any(self, agent_id: str) -> bool:
+        async with self._sf() as session:
+            row = await session.get(AgentRow, agent_id)
+            if row is None:
+                return False
+            await session.delete(row)
+            await session.commit()
+            return True

offline-backend-20260512/backend/packages/harness/deerflow/persistence/skills/base.py

@@ -68,6 +68,14 @@ class SkillStore(ABC):
         """Return the number of skills owned by ``user_id`` (owner_user_id IS NOT NULL)."""
         raise NotImplementedError
 
+    @abstractmethod
+    async def list_all(self) -> list[dict[str, Any]]:
+        """Return every skill record regardless of ownership/visibility.
+
+        Caller is responsible for authorization (admin only).
+        """
+        raise NotImplementedError
+
     @abstractmethod
     async def list_published_names(self) -> set[str]:
         """Return the set of skill names with ``published = True`` (any owner).

offline-backend-20260512/backend/packages/harness/deerflow/persistence/skills/memory.py

@@ -134,5 +134,11 @@ class MemorySkillStore(SkillStore):
     async def count_owned(self, user_id: str) -> int:
         return sum(1 for s in self._skills.values() if s.get("owner_user_id") == user_id)
 
+    async def list_all(self) -> list[dict[str, Any]]:
+        return [
+            _with_derived(_copy(record))  # type: ignore[arg-type]
+            for record in self._skills.values()
+        ]
+
     async def list_published_names(self) -> set[str]:
         return {name for name, record in self._skills.items() if record.get("published")}

offline-backend-20260512/backend/packages/harness/deerflow/persistence/skills/sql.py

@@ -149,6 +149,12 @@ class SkillRepository(SkillStore):
         async with self._sf() as session:
             return await session.scalar(stmt) or 0
 
+    async def list_all(self) -> list[dict[str, Any]]:
+        stmt = select(SkillRow).order_by(SkillRow.created_at.asc())
+        async with self._sf() as session:
+            result = await session.execute(stmt)
+            return [_row_to_dict(row) for row in result.scalars()]
+
     async def list_published_names(self) -> set[str]:
         stmt = select(SkillRow.name).where(SkillRow.published.is_(True))
         async with self._sf() as session: