fix: refine treemap sizing and add earth bgp collectors

Also ensures back-facing satellite selection prevention is in place

.env

@@ -1,25 +0,0 @@
-# Database
-POSTGRES_SERVER=localhost
-POSTGRES_USER=postgres
-POSTGRES_PASSWORD=postgres
-POSTGRES_DB=planet_db
-DATABASE_URL=postgresql+asyncpg://postgres:postgres@localhost:5432/planet_db
-
-# Redis
-REDIS_SERVER=localhost
-REDIS_PORT=6379
-REDIS_URL=redis://localhost:6379/0
-
-# Security
-SECRET_KEY=your-secret-key-change-in-production
-ALGORITHM=HS256
-ACCESS_TOKEN_EXPIRE_MINUTES=15
-REFRESH_TOKEN_EXPIRE_DAYS=7
-
-# API
-API_V1_STR=/api/v1
-PROJECT_NAME="Intelligent Planet Plan"
-VERSION=1.0.0
-
-# CORS
-CORS_ORIGINS=["http://localhost:3000", "http://localhost:8000"]

.gitignore

@@ -41,6 +41,8 @@ MANIFEST
 venv/
 ENV/
 env/
+.uv/
+.uv-cache/
 .ruff_cache/
 *.db
 *.sqlite

.python-version

@@ -0,0 +1 @@
+3.14

.sisyphus/plans/earth-architecture-refactor.md

@@ -0,0 +1,165 @@
+# 地球3D可视化架构重构计划
+
+## 背景
+
+当前 `frontend/public/earth` 3D地球可视化系统基于 Three.js 构建，未来需要迁移到 Unreal Engine (Cesium)。为降低迁移成本，需要提前做好**逻辑与渲染分离**的架构设计。
+
+## 目标
+
+- 将线缆高亮逻辑与渲染实现分离
+- 保持交互逻辑可复用，只需重写渲染层
+- 为后续迁移到 UE/Cesium 做好准备
+
+## 已完成
+
+### 1. 状态枚举定义 (constants.js)
+
+```javascript
+export const CABLE_STATE = {
+  NORMAL: 'normal',
+  HOVERED: 'hovered',
+  LOCKED: 'locked'
+};
+```
+
+### 2. 线缆状态管理 (cables.js - 数据层)
+
+```javascript
+const cableStates = new Map();
+
+export function getCableState(cableId) { ... }
+export function setCableState(cableId, state) { ... }
+export function clearAllCableStates() { ... }
+export function getCableStateInfo() { ... }
+```
+
+### 3. 逻辑层调用 (main.js)
+
+```javascript
+// 悬停
+setCableState(cable.userData.cableId, CABLE_STATE.HOVERED);
+
+// 锁定
+setCableState(cableId, CABLE_STATE.LOCKED);
+
+// 恢复
+setCableState(cableId, CABLE_STATE.NORMAL);
+clearAllCableStates();
+
+// 清除锁定时
+clearLockedObject() {
+  hoveredCable = null;
+  clearAllCableStates();
+  ...
+}
+```
+
+### 4. 渲染层 (main.js - applyCableVisualState)
+
+```javascript
+function applyCableVisualState() {
+  const allCables = getCableLines();
+  const pulse = (Math.sin(Date.now() * CABLE_CONFIG.pulseSpeed) + 1) * 0.5;
+  
+  allCables.forEach(c => {
+    const cableId = c.userData.cableId;
+    const state = getCableState(cableId);
+    
+    switch (state) {
+      case CABLE_STATE.LOCKED:
+        // 呼吸效果 + 白色
+        c.material.opacity = CABLE_CONFIG.lockedOpacityMin + pulse * CABLE_CONFIG.pulseCoefficient;
+        c.material.color.setRGB(1, 1, 1);
+        break;
+      case CABLE_STATE.HOVERED:
+        // 白色高亮
+        c.material.opacity = 1;
+        c.material.color.setRGB(1, 1, 1);
+        break;
+      case CABLE_STATE.NORMAL:
+      default:
+        if (lockedObjectType === 'cable' && lockedObject) {
+          // 其他线缆变暗
+          c.material.opacity = CABLE_CONFIG.otherOpacity;
+          ...
+        } else {
+          // 恢复原始
+          c.material.opacity = 1;
+          c.material.color.setHex(c.userData.originalColor);
+        }
+    }
+  });
+}
+```
+
+## 待完成
+
+### Phase 1: 完善状态配置 (constants.js)
+
+```javascript
+export const CABLE_CONFIG = {
+  lockedOpacityMin: 0.6,
+  lockedOpacityMax: 1.0,
+  otherOpacity: 0.5,
+  otherBrightness: 0.6,
+  pulseSpeed: 0.003,
+  pulseCoefficient: 0.4,
+  // 未来可扩展
+  // lockedLineWidth: 3,
+  // normalLineWidth: 1,
+};
+```
+
+### Phase 2: 卫星状态管理 (satellites.js)
+
+参考线缆状态管理，为卫星添加类似的状态枚举和状态管理函数：
+
+```javascript
+export const SATELLITE_STATE = {
+  NORMAL: 'normal',
+  HOVERED: 'hovered',
+  LOCKED: 'locked'
+};
+```
+
+#### 卫星数据源说明
+
+- **当前使用**: CelesTrak (https://celestrak.org) - 免费，无需认证
+- **后续计划**: Space-Track.org (https://space-track.org) - 需要认证，数据更权威
+- 迁移时只需修改 `satellites.js` 中的数据获取逻辑，状态管理和渲染逻辑不变
+
+### Phase 3: 统一渲染接口
+
+将所有对象的渲染逻辑抽象为一个统一的渲染函数：
+
+```javascript
+function applyObjectVisualState() {
+  applyCableVisualState();
+  applySatelliteVisualState();
+  applyLandingPointVisualState();
+}
+```
+
+### Phase 4: UE 迁移准备
+
+迁移到 Unreal Engine 时：
+1. 保留 `constants.js` 中的枚举和配置
+2. 保留 `cables.js` 中的数据层和状态管理
+3. 保留 `main.js` 中的交互逻辑
+4. **仅重写** `applyCableVisualState()` 等渲染函数
+
+---
+
+## 架构原则
+
+1. **状态与渲染分离** - 对象状态由数据层管理，渲染层只负责根据状态更新视觉效果
+2. **逻辑可复用** - 交互逻辑（点击、悬停、锁定）在迁移时应直接复用
+3. **渲染可替换** - 渲染实现可以针对不同引擎重写，不影响逻辑层
+
+## 文件变更记录
+
+| 日期 | 文件 | 变更 |
+|------|------|------|
+| 2026-03-19 | constants.js | 新增 CABLE_STATE 枚举 |
+| 2026-03-19 | cables.js | 新增状态管理函数 |
+| 2026-03-19 | main.js | 使用状态管理，抽象 applyCableVisualState() |

.sisyphus/plans/predicted-orbit.md

@@ -0,0 +1,136 @@
+# 卫星预测轨道显示功能
+
+## TL;DR
+> 锁定卫星时显示绕地球完整一圈的预测轨道轨迹，从当前位置向外渐变消失
+
+## Context
+
+### 目标
+点击锁定卫星 → 显示该卫星绕地球一周的完整预测轨道（而非当前的历史轨迹）
+
+### 当前实现
+- `TRAIL_LENGTH = 30` - 历史轨迹点数，每帧 push 当前位置
+- 显示最近30帧历史轨迹（类似彗星尾巴）
+
+### 参考: SatelliteMap.space
+- 锁定时显示预测轨道
+- 颜色从当前位置向外渐变消失
+- 使用 satellite.js（与本项目相同）
+
+## 实现状态
+
+### ✅ 已完成
+- [x] 计算卫星轨道周期（基于 `meanMotion`）
+- [x] 生成预测轨道点（10秒采样间隔）
+- [x] 创建独立预测轨道渲染对象
+- [x] 锁定卫星时显示预测轨道
+- [x] 解除锁定时隐藏预测轨道
+- [x] 颜色渐变：当前位置(亮) → 轨道终点(暗)
+- [x] 页面隐藏时清除轨迹（防止切回时闪现）
+
+### 🚧 进行中
+- [ ] 完整圆环轨道（部分卫星因 SGP4 计算问题使用 fallback 圆形轨道）
+- [ ] 每颗卫星只显示一条轨道
+
+## 技术细节
+
+### 轨道周期计算
+```javascript
+function calculateOrbitalPeriod(meanMotion) {
+  return 86400 / meanMotion;
+}
+```
+
+### 预测轨道计算
+```javascript
+function calculatePredictedOrbit(satellite, periodSeconds, sampleInterval = 10) {
+  const points = [];
+  const samples = Math.ceil(periodSeconds / sampleInterval);
+  const now = new Date();
+  
+  // Full orbit: from now to now+period
+  for (let i = 0; i <= samples; i++) {
+    const time = new Date(now.getTime() + i * sampleInterval * 1000);
+    const pos = computeSatellitePosition(satellite, time);
+    if (pos) points.push(pos);
+  }
+  
+  // Fallback: 如果真实位置计算点太少，使用圆形 fallback
+  if (points.length < samples * 0.5) {
+    points.length = 0;
+    // ... 圆形轨道生成
+  }
+  
+  return points;
+}
+```
+
+### 渲染对象
+```javascript
+let predictedOrbitLine = null;
+
+export function showPredictedOrbit(satellite) {
+  hidePredictedOrbit();
+  // ... 计算并渲染轨道
+}
+
+export function hidePredictedOrbit() {
+  if (predictedOrbitLine) {
+    earthObjRef.remove(predictedOrbitLine);
+    predictedOrbitLine.geometry.dispose();
+    predictedOrbitLine.material.dispose();
+    predictedOrbitLine = null;
+  }
+}
+```
+
+## 已知问题
+
+### 1. TLE 格式问题
+`computeSatellitePosition` 使用自行构建的 TLE 格式，对某些卫星返回 null。当前使用 fallback 圆形轨道作为补偿。
+
+### 2. 多条轨道
+部分情况下锁定时会显示多条轨道。需要确保 `hidePredictedOrbit()` 被正确调用。
+
+## 性能考虑
+
+### 点数估算
+| 卫星类型 | 周期 | 10秒采样 | 点数 |
+|---------|------|---------|------|
+| LEO | 90分钟 | 540秒 | ~54点 |
+| MEO | 12小时 | 4320秒 | ~432点 |
+| GEO | 24小时 | 8640秒 | ~864点 |
+
+### 优化策略
+- 当前方案（~900点 GEO）性能可接受
+- 如遇性能问题：GEO 降低采样率到 30秒
+
+## 验证方案
+
+### QA Scenarios
+
+**Scenario: 锁定 Starlink 卫星显示预测轨道**
+1. 打开浏览器，进入 Earth 页面
+2. 显示卫星（点击按钮）
+3. 点击一颗 Starlink 卫星（低轨道 LEO）
+4. 验证：出现黄色预测轨道线，从卫星向外绕行
+5. 验证：颜色从亮黄渐变到暗蓝
+6. 验证：轨道完整闭环
+
+**Scenario: 锁定 GEO 卫星显示预测轨道**
+1. 筛选一颗 GEO 卫星（倾斜角 0-10° 或高轨道）
+2. 点击锁定
+3. 验证：显示完整 24 小时轨道（或 fallback 圆形轨道）
+4. 验证：点数合理（~864点或 fallback）
+
+**Scenario: 解除锁定隐藏预测轨道**
+1. 锁定一颗卫星，显示预测轨道
+2. 点击地球空白处解除锁定
+3. 验证：预测轨道消失
+
+**Scenario: 切换页面后轨迹不闪现**
+1. 锁定一颗卫星
+2. 切换到其他标签页
+3. 等待几秒
+4. 切回页面
+5. 验证：轨迹不突然闪现累积

.sisyphus/plans/webgl-instancing-satellites.md

@@ -0,0 +1,293 @@
+# WebGL Instancing 卫星渲染优化计划
+
+## 背景
+
+当前 `satellites.js` 使用 `THREE.Points` 渲染卫星，受限于 WebGL 点渲染性能，只能显示 ~500-1000 颗卫星。
+需要迁移到真正的 WebGL Instancing 以支持 5000+ 卫星流畅渲染。
+
+## 技术选型
+
+| 方案 | 性能 | 改动量 | 维护性 | 推荐 |
+|------|------|--------|--------|------|
+| THREE.Points (现状) | ★★☆ | - | - | 基准 |
+| THREE.InstancedMesh | ★★★ | 中 | 高 | 不适合点 |
+| InstancedBufferGeometry + 自定义Shader | ★★★★ | 中高 | 中 | ✅ 推荐 |
+| 迁移到 TWGL.js / Raw WebGL | ★★★★★ | 高 | 低 | 未来UE |
+
+**推荐方案**: InstancedBufferGeometry + 自定义 Shader
+- 保持 Three.js 架构
+- 复用 satellite.js 数据层
+- 性能接近原生 WebGL
+
+---
+
+## Phase 1: 调研与原型
+
+### 1.1 分析现有架构
+
+**现状 (satellites.js)**:
+```javascript
+// 创建点云
+const pointsGeometry = new THREE.BufferGeometry();
+pointsGeometry.setAttribute('position', new THREE.BufferAttribute(positions, 3));
+pointsGeometry.setAttribute('color', new THREE.BufferAttribute(colors, 3));
+
+const pointsMaterial = new THREE.PointsMaterial({
+  size: 2,
+  vertexColors: true,
+  transparent: true,
+  opacity: 0.8,
+  sizeAttenuation: true
+});
+
+satellitePoints = new THREE.Points(pointsGeometry, pointsMaterial);
+```
+
+**问题**: 每个卫星作为一个顶点，GPU 需要处理 ~500 个 draw calls (取决于视锥体裁剪)
+
+### 1.2 Instanced Rendering 原理
+
+```javascript
+// 目标：单次 draw call 渲染所有卫星
+// 每个卫星属性:
+// - position (vec3): 位置
+// - color (vec3): 颜色
+// - size (float): 大小 (可选)
+// - selected (float): 是否选中 (0/1)
+
+// 使用 InstancedBufferGeometry
+const geometry = new THREE.InstancedBufferGeometry();
+geometry.index = originalGeometry.index;
+geometry.attributes.position = originalGeometry.attributes.position;
+geometry.attributes.uv = originalGeometry.attributes.uv;
+
+// 实例数据
+const instancePositions = new Float32Array(satelliteCount * 3);
+const instanceColors = new Float32Array(satelliteCount * 3);
+
+geometry.setAttribute('instancePosition', 
+  new THREE.InstancedBufferAttribute(instancePositions, 3));
+geometry.setAttribute('instanceColor', 
+  new THREE.InstancedBufferAttribute(instanceColors, 3));
+
+// 自定义 Shader
+const material = new THREE.ShaderMaterial({
+  vertexShader: `
+    attribute vec3 instancePosition;
+    attribute vec3 instanceColor;
+    varying vec3 vColor;
+    
+    void main() {
+      vColor = instanceColor;
+      vec3 transformed = position + instancePosition;
+      gl_Position = projectionMatrix * modelViewMatrix * vec4(transformed, 1.0);
+    }
+  `,
+  fragmentShader: `
+    varying vec3 vColor;
+    void main() {
+      gl_FragColor = vec4(vColor, 0.8);
+    }
+  `
+});
+```
+
+---
+
+## Phase 2: 实现
+
+### 2.1 创建 instanced-satellites.js
+
+```javascript
+// instanced-satellites.js - Instanced rendering for satellites
+
+import * as THREE from 'three';
+import { SATELLITE_CONFIG } from './constants.js';
+
+let instancedMesh = null;
+let satelliteData = [];
+let instancePositions = null;
+let instanceColors = null;
+let satelliteCount = 0;
+
+const SATELLITE_VERTEX_SHADER = `
+  attribute vec3 instancePosition;
+  attribute vec3 instanceColor;
+  attribute float instanceSize;
+  
+  varying vec3 vColor;
+  
+  void main() {
+    vColor = instanceColor;
+    vec3 transformed = position * instanceSize + instancePosition;
+    gl_Position = projectionMatrix * modelViewMatrix * vec4(transformed, 1.0);
+  }
+`;
+
+const SATELLITE_FRAGMENT_SHADER = `
+  varying vec3 vColor;
+  
+  void main() {
+    gl_FragColor = vec4(vColor, 0.9);
+  }
+`;
+
+export function createInstancedSatellites(scene, earthObj) {
+  // 基础球体几何 (每个卫星是一个小圆点)
+  const baseGeometry = new THREE.CircleGeometry(1, 8);
+  
+  // 创建 InstancedBufferGeometry
+  const geometry = new THREE.InstancedBufferGeometry();
+  geometry.index = baseGeometry.index;
+  geometry.attributes.position = baseGeometry.attributes.position;
+  geometry.attributes.uv = baseGeometry.attributes.uv;
+  
+  // 初始化实例数据数组 (稍后填充)
+  instancePositions = new Float32Array(MAX_SATELLITES * 3);
+  instanceColors = new Float32Array(MAX_SATELLITES * 3);
+  const instanceSizes = new Float32Array(MAX_SATELLITES);
+  
+  geometry.setAttribute('instancePosition', 
+    new THREE.InstancedBufferAttribute(instancePositions, 3));
+  geometry.setAttribute('instanceColor', 
+    new THREE.InstancedBufferAttribute(instanceColors, 3));
+  geometry.setAttribute('instanceSize', 
+    new THREE.InstancedBufferAttribute(instanceSizes, 1));
+  
+  const material = new THREE.ShaderMaterial({
+    vertexShader: SATELLITE_VERTEX_SHADER,
+    fragmentShader: SATELLITE_FRAGMENT_SHADER,
+    transparent: true,
+    side: THREE.DoubleSide
+  });
+  
+  instancedMesh = new THREE.Mesh(geometry, material);
+  instancedMesh.frustumCulled = false; // 我们自己处理裁剪
+  scene.add(instancedMesh);
+  
+  return instancedMesh;
+}
+
+export function updateInstancedSatellites(satellitePositions) {
+  // satellitePositions: Array of { position: Vector3, color: Color }
+  const count = Math.min(satellitePositions.length, MAX_SATELLITES);
+  
+  for (let i = 0; i < count; i++) {
+    const sat = satellitePositions[i];
+    instancePositions[i * 3] = sat.position.x;
+    instancePositions[i * 3 + 1] = sat.position.y;
+    instancePositions[i * 3 + 2] = sat.position.z;
+    
+    instanceColors[i * 3] = sat.color.r;
+    instanceColors[i * 3 + 1] = sat.color.g;
+    instanceColors[i * 3 + 2] = sat.color.b;
+  }
+  
+  instancedMesh.geometry.attributes.instancePosition.needsUpdate = true;
+  instancedMesh.geometry.attributes.instanceColor.needsUpdate = true;
+  instancedMesh.geometry.setDrawRange(0, count);
+}
+```
+
+### 2.2 修改现有 satellites.js
+
+保持数据层不变，添加新渲染模式：
+
+```javascript
+// 添加配置
+export const SATELLITE_CONFIG = {
+  USE_INSTANCING: true,  // 切换渲染模式
+  MAX_SATELLITES: 5000,
+  SATELLITE_SIZE: 0.5,
+  // ...
+};
+```
+
+### 2.3 性能优化点
+
+1. **GPU 实例化**: 单次 draw call 渲染所有卫星
+2. **批量更新**: 所有位置/颜色一次更新
+3. **视锥体裁剪**: 自定义裁剪逻辑，避免 CPU 端逐卫星检测
+4. **LOD (可选)**: 远处卫星简化显示
+
+---
+
+## Phase 3: 与现有系统集成
+
+### 3.1 悬停/选中处理
+
+当前通过 `selectSatellite()` 设置选中状态，Instanced 模式下需要：
+
+```javascript
+// 在 shader 中通过 instanceId 判断是否选中
+// 或者使用单独的 InstancedBufferAttribute 存储选中状态
+const instanceSelected = new Float32Array(MAX_SATELLITES);
+geometry.setAttribute('instanceSelected', 
+  new THREE.InstancedBufferAttribute(instanceSelected, 1));
+```
+
+### 3.2 轨迹线
+
+轨迹线仍然使用 `THREE.Line` 或 `THREE.LineSegments`，但可以类似地 Instanced 化：
+
+```javascript
+// Instanced LineSegments for trails
+const trailGeometry = new THREE.InstancedBufferGeometry();
+trailGeometry.setAttribute('position', trailPositions);
+trailGeometry.setAttribute('instanceStart', ...);
+trailGeometry.setAttribute('instanceEnd', ...);
+```
+
+---
+
+## Phase 4: 验证与调优
+
+### 4.1 性能测试
+
+| 卫星数量 | Points 模式 | Instanced 模式 |
+|----------|-------------|----------------|
+| 500 | ✅ 60fps | ✅ 60fps |
+| 2000 | ⚠️ 30fps | ✅ 60fps |
+| 5000 | ❌ 10fps | ✅ 45fps |
+| 10000 | ❌ 卡顿 | ⚠️ 30fps |
+
+### 4.2 可能遇到的问题
+
+1. **Shader 编译错误**: 需要调试 GLSL
+2. **实例数量限制**: GPU 最大实例数 (通常 65535)
+3. **大小不一**: 需要 per-instance size 属性
+4. **透明度排序**: Instanced 渲染透明度处理复杂
+
+---
+
+## 文件变更清单
+
+| 文件 | 变更 |
+|------|------|
+| `constants.js` | 新增 `SATELLITE_CONFIG` |
+| `satellites.js` | 添加 Instanced 模式支持 |
+| `instanced-satellites.js` | 新文件 - Instanced 渲染核心 |
+| `main.js` | 集成新渲染模块 |
+
+---
+
+## 时间估算
+
+| Phase | 工作量 | 难度 |
+|-------|--------|------|
+| Phase 1 | 1-2 天 | 低 |
+| Phase 2 | 2-3 天 | 中 |
+| Phase 3 | 1-2 天 | 中 |
+| Phase 4 | 1 天 | 低 |
+| **总计** | **5-8 天** | - |
+
+---
+
+## 替代方案考虑
+
+如果 Phase 2 实施困难，可以考虑：
+
+1. **使用 Three.js InstancedMesh**: 适合渲染小型 3D 模型替代点
+2. **使用 pointcloud2 格式**: 类似 LiDAR 点云渲染
+3. **Web Workers**: 将轨道计算移到 Worker 线程
+4. **迁移到 Cesium**: Cesium 原生支持 Instancing，且是 UE 迁移的中间步骤

README.md

@@ -184,14 +184,20 @@
 ## 快速启动
 
 ```bash
-# 启动全部服务
+# 启动前后端服务
-docker-compose up -d
+./planet.sh start
 
-# 仅启动后端
+# 仅重启后端
-cd backend && python -m uvicorn app.main:app --reload
+./planet.sh restart -b
 
-# 仅启动前端
+# 仅重启前端
-cd frontend && npm run dev
+./planet.sh restart -f
+
+# 交互创建用户
+./planet.sh createuser
+
+# 查看服务状态
+./planet.sh health
 ```
 
 ## API 文档

VERSION

@@ -0,0 +1 @@
+0.21.7

backend/Dockerfile

@@ -16,4 +16,4 @@ COPY . .
 
 EXPOSE 8000
 
-CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]

backend/app/api/main.py

@@ -11,6 +11,7 @@ from app.api.v1 import (
     settings,
     collected_data,
     visualization,
+    bgp,
 )
 
 api_router = APIRouter()
@@ -27,3 +28,4 @@ api_router.include_router(dashboard.router, prefix="/dashboard", tags=["dashboar
 api_router.include_router(alerts.router, prefix="/alerts", tags=["alerts"])
 api_router.include_router(settings.router, prefix="/settings", tags=["settings"])
 api_router.include_router(visualization.router, prefix="/visualization", tags=["visualization"])
+api_router.include_router(bgp.router, prefix="/bgp", tags=["bgp"])

backend/app/api/v1/alerts.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import UTC, datetime
 from typing import Optional
 
 from fastapi import APIRouter, Depends
@@ -10,6 +10,7 @@ from app.models.user import User
 from app.core.security import get_current_user
 from app.models.alert import Alert, AlertSeverity, AlertStatus
 
+
 router = APIRouter()
 
 
@@ -67,7 +68,7 @@ async def acknowledge_alert(
 
     alert.status = AlertStatus.ACKNOWLEDGED
     alert.acknowledged_by = current_user.id
-    alert.acknowledged_at = datetime.utcnow()
+    alert.acknowledged_at = datetime.now(UTC)
     await db.commit()
 
     return {"message": "Alert acknowledged", "alert": alert.to_dict()}
@@ -88,7 +89,7 @@ async def resolve_alert(
 
     alert.status = AlertStatus.RESOLVED
     alert.resolved_by = current_user.id
-    alert.resolved_at = datetime.utcnow()
+    alert.resolved_at = datetime.now(UTC)
     alert.resolution_notes = resolution
     await db.commit()
 

backend/app/api/v1/bgp.py

@@ -0,0 +1,182 @@
+from datetime import datetime
+from typing import Optional
+
+from fastapi import APIRouter, Depends, HTTPException, Query
+from sqlalchemy import func, select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.core.security import get_current_user
+from app.db.session import get_db
+from app.models.bgp_anomaly import BGPAnomaly
+from app.models.collected_data import CollectedData
+from app.models.user import User
+
+router = APIRouter()
+
+BGP_SOURCES = ("ris_live_bgp", "bgpstream_bgp")
+
+
+def _parse_dt(value: Optional[str]) -> Optional[datetime]:
+    if not value:
+        return None
+    return datetime.fromisoformat(value.replace("Z", "+00:00"))
+
+
+def _matches_time(value: Optional[datetime], time_from: Optional[datetime], time_to: Optional[datetime]) -> bool:
+    if value is None:
+        return False
+    if time_from and value < time_from:
+        return False
+    if time_to and value > time_to:
+        return False
+    return True
+
+
+@router.get("/events")
+async def list_bgp_events(
+    prefix: Optional[str] = Query(None),
+    origin_asn: Optional[int] = Query(None),
+    peer_asn: Optional[int] = Query(None),
+    collector: Optional[str] = Query(None),
+    event_type: Optional[str] = Query(None),
+    source: Optional[str] = Query(None),
+    time_from: Optional[str] = Query(None),
+    time_to: Optional[str] = Query(None),
+    page: int = Query(1, ge=1),
+    page_size: int = Query(50, ge=1, le=200),
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    stmt = (
+        select(CollectedData)
+        .where(CollectedData.source.in_(BGP_SOURCES))
+        .order_by(CollectedData.reference_date.desc().nullslast(), CollectedData.id.desc())
+    )
+    if source:
+        stmt = stmt.where(CollectedData.source == source)
+
+    result = await db.execute(stmt)
+    records = result.scalars().all()
+    dt_from = _parse_dt(time_from)
+    dt_to = _parse_dt(time_to)
+
+    filtered = []
+    for record in records:
+        metadata = record.extra_data or {}
+        if prefix and metadata.get("prefix") != prefix:
+            continue
+        if origin_asn is not None and metadata.get("origin_asn") != origin_asn:
+            continue
+        if peer_asn is not None and metadata.get("peer_asn") != peer_asn:
+            continue
+        if collector and metadata.get("collector") != collector:
+            continue
+        if event_type and metadata.get("event_type") != event_type:
+            continue
+        if (dt_from or dt_to) and not _matches_time(record.reference_date, dt_from, dt_to):
+            continue
+        filtered.append(record)
+
+    offset = (page - 1) * page_size
+    return {
+        "total": len(filtered),
+        "page": page,
+        "page_size": page_size,
+        "data": [record.to_dict() for record in filtered[offset : offset + page_size]],
+    }
+
+
+@router.get("/events/{event_id}")
+async def get_bgp_event(
+    event_id: int,
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    record = await db.get(CollectedData, event_id)
+    if not record or record.source not in BGP_SOURCES:
+        raise HTTPException(status_code=404, detail="BGP event not found")
+    return record.to_dict()
+
+
+@router.get("/anomalies")
+async def list_bgp_anomalies(
+    severity: Optional[str] = Query(None),
+    anomaly_type: Optional[str] = Query(None),
+    status: Optional[str] = Query(None),
+    prefix: Optional[str] = Query(None),
+    origin_asn: Optional[int] = Query(None),
+    time_from: Optional[str] = Query(None),
+    time_to: Optional[str] = Query(None),
+    page: int = Query(1, ge=1),
+    page_size: int = Query(50, ge=1, le=200),
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    stmt = select(BGPAnomaly).order_by(BGPAnomaly.created_at.desc(), BGPAnomaly.id.desc())
+    if severity:
+        stmt = stmt.where(BGPAnomaly.severity == severity)
+    if anomaly_type:
+        stmt = stmt.where(BGPAnomaly.anomaly_type == anomaly_type)
+    if status:
+        stmt = stmt.where(BGPAnomaly.status == status)
+    if prefix:
+        stmt = stmt.where(BGPAnomaly.prefix == prefix)
+    if origin_asn is not None:
+        stmt = stmt.where(BGPAnomaly.origin_asn == origin_asn)
+
+    result = await db.execute(stmt)
+    records = result.scalars().all()
+    dt_from = _parse_dt(time_from)
+    dt_to = _parse_dt(time_to)
+    if dt_from or dt_to:
+        records = [record for record in records if _matches_time(record.created_at, dt_from, dt_to)]
+
+    offset = (page - 1) * page_size
+    return {
+        "total": len(records),
+        "page": page,
+        "page_size": page_size,
+        "data": [record.to_dict() for record in records[offset : offset + page_size]],
+    }
+
+
+@router.get("/anomalies/summary")
+async def get_bgp_anomaly_summary(
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    total_result = await db.execute(select(func.count(BGPAnomaly.id)))
+    type_result = await db.execute(
+        select(BGPAnomaly.anomaly_type, func.count(BGPAnomaly.id))
+        .group_by(BGPAnomaly.anomaly_type)
+        .order_by(func.count(BGPAnomaly.id).desc())
+    )
+    severity_result = await db.execute(
+        select(BGPAnomaly.severity, func.count(BGPAnomaly.id))
+        .group_by(BGPAnomaly.severity)
+        .order_by(func.count(BGPAnomaly.id).desc())
+    )
+    status_result = await db.execute(
+        select(BGPAnomaly.status, func.count(BGPAnomaly.id))
+        .group_by(BGPAnomaly.status)
+        .order_by(func.count(BGPAnomaly.id).desc())
+    )
+
+    return {
+        "total": total_result.scalar() or 0,
+        "by_type": {row[0]: row[1] for row in type_result.fetchall()},
+        "by_severity": {row[0]: row[1] for row in severity_result.fetchall()},
+        "by_status": {row[0]: row[1] for row in status_result.fetchall()},
+    }
+
+
+@router.get("/anomalies/{anomaly_id}")
+async def get_bgp_anomaly(
+    anomaly_id: int,
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    record = await db.get(BGPAnomaly, anomaly_id)
+    if not record:
+        raise HTTPException(status_code=404, detail="BGP anomaly not found")
+    return record.to_dict()

backend/app/api/v1/collected_data.py

@@ -7,16 +7,138 @@ import json
 import csv
 import io
 
+from app.core.collected_data_fields import get_metadata_field
+from app.core.countries import COUNTRY_OPTIONS, get_country_search_variants, normalize_country
+from app.core.time import to_iso8601_utc
 from app.db.session import get_db
 from app.models.user import User
 from app.core.security import get_current_user
 from app.models.collected_data import CollectedData
+from app.models.datasource import DataSource
 
 router = APIRouter()
 
 
+COUNTRY_SQL = "metadata->>'country'"
+SEARCHABLE_SQL = [
+    "name",
+    "title",
+    "description",
+    "source",
+    "data_type",
+    "source_id",
+    "metadata::text",
+]
+
+
+def parse_multi_values(value: Optional[str]) -> list[str]:
+    if not value:
+        return []
+    return [item.strip() for item in value.split(",") if item.strip()]
+
+
+def build_in_condition(field_sql: str, values: list[str], param_prefix: str, params: dict) -> str:
+    placeholders = []
+    for index, value in enumerate(values):
+        key = f"{param_prefix}_{index}"
+        params[key] = value
+        placeholders.append(f":{key}")
+    return f"{field_sql} IN ({', '.join(placeholders)})"
+
+
+def build_search_condition(search: Optional[str], params: dict) -> Optional[str]:
+    if not search:
+        return None
+
+    normalized = search.strip()
+    if not normalized:
+        return None
+
+    search_terms = [normalized]
+    for variant in get_country_search_variants(normalized):
+        if variant.casefold() not in {term.casefold() for term in search_terms}:
+            search_terms.append(variant)
+
+    conditions = []
+    for index, term in enumerate(search_terms):
+        params[f"search_{index}"] = f"%{term}%"
+        conditions.extend(f"{field} ILIKE :search_{index}" for field in SEARCHABLE_SQL)
+
+    params["search_exact"] = normalized
+    params["search_prefix"] = f"{normalized}%"
+
+    canonical_variants = get_country_search_variants(normalized)
+    canonical = canonical_variants[0] if canonical_variants else None
+    params["country_search_exact"] = canonical or normalized
+    params["country_search_prefix"] = f"{(canonical or normalized)}%"
+
+    return "(" + " OR ".join(conditions) + ")"
+
+
+def build_search_rank_sql(search: Optional[str]) -> str:
+    if not search or not search.strip():
+        return "0"
+
+    return """
+        CASE
+            WHEN name ILIKE :search_exact THEN 700
+            WHEN name ILIKE :search_prefix THEN 600
+            WHEN title ILIKE :search_exact THEN 500
+            WHEN title ILIKE :search_prefix THEN 400
+            WHEN metadata->>'country' ILIKE :country_search_exact THEN 380
+            WHEN metadata->>'country' ILIKE :country_search_prefix THEN 340
+            WHEN source_id ILIKE :search_exact THEN 350
+            WHEN source ILIKE :search_exact THEN 300
+            WHEN data_type ILIKE :search_exact THEN 250
+            WHEN description ILIKE :search_0 THEN 150
+            WHEN metadata::text ILIKE :search_0 THEN 100
+            WHEN title ILIKE :search_0 THEN 80
+            WHEN name ILIKE :search_0 THEN 60
+            WHEN source ILIKE :search_0 THEN 40
+            WHEN data_type ILIKE :search_0 THEN 30
+            WHEN source_id ILIKE :search_0 THEN 20
+            ELSE 0
+        END
+    """
+
+
+def serialize_collected_row(row, source_name_map: dict[str, str] | None = None) -> dict:
+    metadata = row[7]
+    source = row[1]
+    return {
+        "id": row[0],
+        "source": source,
+        "source_name": source_name_map.get(source, source) if source_name_map else source,
+        "source_id": row[2],
+        "data_type": row[3],
+        "name": row[4],
+        "title": row[5],
+        "description": row[6],
+        "country": get_metadata_field(metadata, "country"),
+        "city": get_metadata_field(metadata, "city"),
+        "latitude": get_metadata_field(metadata, "latitude"),
+        "longitude": get_metadata_field(metadata, "longitude"),
+        "value": get_metadata_field(metadata, "value"),
+        "unit": get_metadata_field(metadata, "unit"),
+        "metadata": metadata,
+        "cores": get_metadata_field(metadata, "cores"),
+        "rmax": get_metadata_field(metadata, "rmax"),
+        "rpeak": get_metadata_field(metadata, "rpeak"),
+        "power": get_metadata_field(metadata, "power"),
+        "collected_at": to_iso8601_utc(row[8]),
+        "reference_date": to_iso8601_utc(row[9]),
+        "is_valid": row[10],
+    }
+
+
+async def get_source_name_map(db: AsyncSession) -> dict[str, str]:
+    result = await db.execute(select(DataSource.source, DataSource.name))
+    return {row[0]: row[1] for row in result.fetchall()}
+
+
 @router.get("")
 async def list_collected_data(
+    mode: str = Query("current", description="查询模式: current/history"),
     source: Optional[str] = Query(None, description="数据源过滤"),
     data_type: Optional[str] = Query(None, description="数据类型过滤"),
     country: Optional[str] = Query(None, description="国家过滤"),
@@ -27,25 +149,30 @@ async def list_collected_data(
     db: AsyncSession = Depends(get_db),
 ):
     """查询采集的数据列表"""
+    normalized_country = normalize_country(country) if country else None
+    source_values = parse_multi_values(source)
+    data_type_values = parse_multi_values(data_type)
 
     # Build WHERE clause
     conditions = []
     params = {}
 
-    if source:
+    if mode != "history":
-        conditions.append("source = :source")
+        conditions.append("COALESCE(is_current, TRUE) = TRUE")
-        params["source"] = source
+
-    if data_type:
+    if source_values:
-        conditions.append("data_type = :data_type")
+        conditions.append(build_in_condition("source", source_values, "source", params))
-        params["data_type"] = data_type
+    if data_type_values:
-    if country:
+        conditions.append(build_in_condition("data_type", data_type_values, "data_type", params))
-        conditions.append("country = :country")
+    if normalized_country:
-        params["country"] = country
+        conditions.append(f"{COUNTRY_SQL} = :country")
-    if search:
+        params["country"] = normalized_country
-        conditions.append("(name ILIKE :search OR title ILIKE :search)")
+    search_condition = build_search_condition(search, params)
-        params["search"] = f"%{search}%"
+    if search_condition:
+        conditions.append(search_condition)
 
     where_sql = " AND ".join(conditions) if conditions else "1=1"
+    search_rank_sql = build_search_rank_sql(search)
 
     # Calculate offset
     offset = (page - 1) * page_size
@@ -58,11 +185,11 @@ async def list_collected_data(
     # Query data
     query = text(f"""
         SELECT id, source, source_id, data_type, name, title, description,
-               country, city, latitude, longitude, value, unit,
+               metadata, collected_at, reference_date, is_valid,
-               metadata, collected_at, reference_date, is_valid
+               {search_rank_sql} AS search_rank
         FROM collected_data
         WHERE {where_sql}
-        ORDER BY collected_at DESC
+        ORDER BY search_rank DESC, collected_at DESC
         LIMIT :limit OFFSET :offset
     """)
     params["limit"] = page_size
@@ -70,30 +197,11 @@ async def list_collected_data(
 
     result = await db.execute(query, params)
     rows = result.fetchall()
+    source_name_map = await get_source_name_map(db)
 
     data = []
     for row in rows:
-        data.append(
+        data.append(serialize_collected_row(row[:11], source_name_map))
-            {
-                "id": row[0],
-                "source": row[1],
-                "source_id": row[2],
-                "data_type": row[3],
-                "name": row[4],
-                "title": row[5],
-                "description": row[6],
-                "country": row[7],
-                "city": row[8],
-                "latitude": row[9],
-                "longitude": row[10],
-                "value": row[11],
-                "unit": row[12],
-                "metadata": row[13],
-                "collected_at": row[14].isoformat() if row[14] else None,
-                "reference_date": row[15].isoformat() if row[15] else None,
-                "is_valid": row[16],
-            }
-        )
 
     return {
         "total": total,
@@ -105,21 +213,39 @@ async def list_collected_data(
 
 @router.get("/summary")
 async def get_data_summary(
+    mode: str = Query("current", description="查询模式: current/history"),
+    source: Optional[str] = Query(None, description="数据源过滤"),
+    data_type: Optional[str] = Query(None, description="数据类型过滤"),
+    country: Optional[str] = Query(None, description="国家过滤"),
+    search: Optional[str] = Query(None, description="搜索名称"),
     current_user: User = Depends(get_current_user),
     db: AsyncSession = Depends(get_db),
 ):
     """获取数据汇总统计"""
+    where_sql, params = build_where_clause(source, data_type, country, search)
+    if mode != "history":
+        where_sql = f"({where_sql}) AND COALESCE(is_current, TRUE) = TRUE"
+
+    overall_where_sql = "COALESCE(is_current, TRUE) = TRUE" if mode != "history" else "1=1"
+
+    overall_total_result = await db.execute(
+        text(f"SELECT COUNT(*) FROM collected_data WHERE {overall_where_sql}")
+    )
+    overall_total = overall_total_result.scalar() or 0
 
     # By source and data_type
     result = await db.execute(
-        text("""
+        text(f"""
         SELECT source, data_type, COUNT(*) as count
         FROM collected_data
+        WHERE {where_sql}
         GROUP BY source, data_type
         ORDER BY source, data_type
-    """)
+    """),
+        params,
     )
     rows = result.fetchall()
+    source_name_map = await get_source_name_map(db)
 
     by_source = {}
     total = 0
@@ -128,31 +254,62 @@ async def get_data_summary(
         data_type = row[1]
         count = row[2]
 
-        if source not in by_source:
+        source_key = source_name_map.get(source, source)
-            by_source[source] = {}
+        if source_key not in by_source:
-        by_source[source][data_type] = count
+            by_source[source_key] = {}
+        by_source[source_key][data_type] = count
         total += count
 
     # Total by source
     source_totals = await db.execute(
-        text("""
+        text(f"""
         SELECT source, COUNT(*) as count
         FROM collected_data
+        WHERE {where_sql}
         GROUP BY source
         ORDER BY count DESC
-    """)
+    """),
+        params,
     )
     source_rows = source_totals.fetchall()
 
+    type_totals = await db.execute(
+        text(f"""
+        SELECT data_type, COUNT(*) as count
+        FROM collected_data
+        WHERE {where_sql}
+        GROUP BY data_type
+        ORDER BY count DESC, data_type
+    """),
+        params,
+    )
+    type_rows = type_totals.fetchall()
+
     return {
         "total_records": total,
+        "overall_total_records": overall_total,
         "by_source": by_source,
-        "source_totals": [{"source": row[0], "count": row[1]} for row in source_rows],
+        "source_totals": [
+            {
+                "source": row[0],
+                "source_name": source_name_map.get(row[0], row[0]),
+                "count": row[1],
+            }
+            for row in source_rows
+        ],
+        "type_totals": [
+            {
+                "data_type": row[0],
+                "count": row[1],
+            }
+            for row in type_rows
+        ],
     }
 
 
 @router.get("/sources")
 async def get_data_sources(
+    mode: str = Query("current", description="查询模式: current/history"),
     current_user: User = Depends(get_current_user),
     db: AsyncSession = Depends(get_db),
 ):
@@ -160,18 +317,25 @@ async def get_data_sources(
 
     result = await db.execute(
         text("""
-        SELECT DISTINCT source FROM collected_data ORDER BY source
+        SELECT DISTINCT source FROM collected_data
+        """ + ("WHERE COALESCE(is_current, TRUE) = TRUE " if mode != "history" else "") + """
+        ORDER BY source
     """)
     )
     rows = result.fetchall()
+    source_name_map = await get_source_name_map(db)
 
     return {
-        "sources": [row[0] for row in rows],
+        "sources": [
+            {"source": row[0], "source_name": source_name_map.get(row[0], row[0])}
+            for row in rows
+        ],
     }
 
 
 @router.get("/types")
 async def get_data_types(
+    mode: str = Query("current", description="查询模式: current/history"),
     current_user: User = Depends(get_current_user),
     db: AsyncSession = Depends(get_db),
 ):
@@ -179,7 +343,9 @@ async def get_data_types(
 
     result = await db.execute(
         text("""
-        SELECT DISTINCT data_type FROM collected_data ORDER BY data_type
+        SELECT DISTINCT data_type FROM collected_data
+        """ + ("WHERE COALESCE(is_current, TRUE) = TRUE " if mode != "history" else "") + """
+        ORDER BY data_type
     """)
     )
     rows = result.fetchall()
@@ -196,17 +362,8 @@ async def get_countries(
 ):
     """获取所有国家列表"""
 
-    result = await db.execute(
-        text("""
-        SELECT DISTINCT country FROM collected_data
-        WHERE country IS NOT NULL AND country != ''
-        ORDER BY country
-    """)
-    )
-    rows = result.fetchall()
-
     return {
-        "countries": [row[0] for row in rows],
+        "countries": COUNTRY_OPTIONS,
     }
 
 
@@ -221,7 +378,6 @@ async def get_collected_data(
     result = await db.execute(
         text("""
             SELECT id, source, source_id, data_type, name, title, description,
-                   country, city, latitude, longitude, value, unit,
                    metadata, collected_at, reference_date, is_valid
             FROM collected_data
             WHERE id = :id
@@ -236,25 +392,8 @@ async def get_collected_data(
             detail="数据不存在",
         )
 
-    return {
+    source_name_map = await get_source_name_map(db)
-        "id": row[0],
+    return serialize_collected_row(row, source_name_map)
-        "source": row[1],
-        "source_id": row[2],
-        "data_type": row[3],
-        "name": row[4],
-        "title": row[5],
-        "description": row[6],
-        "country": row[7],
-        "city": row[8],
-        "latitude": row[9],
-        "longitude": row[10],
-        "value": row[11],
-        "unit": row[12],
-        "metadata": row[13],
-        "collected_at": row[14].isoformat() if row[14] else None,
-        "reference_date": row[15].isoformat() if row[15] else None,
-        "is_valid": row[16],
-    }
 
 
 def build_where_clause(
@@ -263,19 +402,21 @@ def build_where_clause(
     """Build WHERE clause and params for queries"""
     conditions = []
     params = {}
+    source_values = parse_multi_values(source)
+    data_type_values = parse_multi_values(data_type)
 
-    if source:
+    if source_values:
-        conditions.append("source = :source")
+        conditions.append(build_in_condition("source", source_values, "source", params))
-        params["source"] = source
+    if data_type_values:
-    if data_type:
+        conditions.append(build_in_condition("data_type", data_type_values, "data_type", params))
-        conditions.append("data_type = :data_type")
+    normalized_country = normalize_country(country) if country else None
-        params["data_type"] = data_type
+
-    if country:
+    if normalized_country:
-        conditions.append("country = :country")
+        conditions.append(f"{COUNTRY_SQL} = :country")
-        params["country"] = country
+        params["country"] = normalized_country
-    if search:
+    search_condition = build_search_condition(search, params)
-        conditions.append("(name ILIKE :search OR title ILIKE :search)")
+    if search_condition:
-        params["search"] = f"%{search}%"
+        conditions.append(search_condition)
 
     where_sql = " AND ".join(conditions) if conditions else "1=1"
     return where_sql, params
@@ -283,6 +424,7 @@ def build_where_clause(
 
 @router.get("/export/json")
 async def export_json(
+    mode: str = Query("current", description="查询模式: current/history"),
     source: Optional[str] = Query(None, description="数据源过滤"),
     data_type: Optional[str] = Query(None, description="数据类型过滤"),
     country: Optional[str] = Query(None, description="国家过滤"),
@@ -294,11 +436,12 @@ async def export_json(
     """导出数据为 JSON 格式"""
 
     where_sql, params = build_where_clause(source, data_type, country, search)
+    if mode != "history":
+        where_sql = f"({where_sql}) AND COALESCE(is_current, TRUE) = TRUE"
     params["limit"] = limit
 
     query = text(f"""
         SELECT id, source, source_id, data_type, name, title, description,
-               country, city, latitude, longitude, value, unit,
                metadata, collected_at, reference_date, is_valid
         FROM collected_data
         WHERE {where_sql}
@@ -311,27 +454,7 @@ async def export_json(
 
     data = []
     for row in rows:
-        data.append(
+        data.append(serialize_collected_row(row))
-            {
-                "id": row[0],
-                "source": row[1],
-                "source_id": row[2],
-                "data_type": row[3],
-                "name": row[4],
-                "title": row[5],
-                "description": row[6],
-                "country": row[7],
-                "city": row[8],
-                "latitude": row[9],
-                "longitude": row[10],
-                "value": row[11],
-                "unit": row[12],
-                "metadata": row[13],
-                "collected_at": row[14].isoformat() if row[14] else None,
-                "reference_date": row[15].isoformat() if row[15] else None,
-                "is_valid": row[16],
-            }
-        )
 
     json_str = json.dumps({"data": data, "total": len(data)}, ensure_ascii=False, indent=2)
 
@@ -346,6 +469,7 @@ async def export_json(
 
 @router.get("/export/csv")
 async def export_csv(
+    mode: str = Query("current", description="查询模式: current/history"),
     source: Optional[str] = Query(None, description="数据源过滤"),
     data_type: Optional[str] = Query(None, description="数据类型过滤"),
     country: Optional[str] = Query(None, description="国家过滤"),
@@ -357,11 +481,12 @@ async def export_csv(
     """导出数据为 CSV 格式"""
 
     where_sql, params = build_where_clause(source, data_type, country, search)
+    if mode != "history":
+        where_sql = f"({where_sql}) AND COALESCE(is_current, TRUE) = TRUE"
     params["limit"] = limit
 
     query = text(f"""
         SELECT id, source, source_id, data_type, name, title, description,
-               country, city, latitude, longitude, value, unit,
                metadata, collected_at, reference_date, is_valid
         FROM collected_data
         WHERE {where_sql}
@@ -409,16 +534,16 @@ async def export_csv(
                 row[4],
                 row[5],
                 row[6],
-                row[7],
+                get_metadata_field(row[7], "country"),
-                row[8],
+                get_metadata_field(row[7], "city"),
-                row[9],
+                get_metadata_field(row[7], "latitude"),
+                get_metadata_field(row[7], "longitude"),
+                get_metadata_field(row[7], "value"),
+                get_metadata_field(row[7], "unit"),
+                json.dumps(row[7]) if row[7] else "",
+                to_iso8601_utc(row[8]) or "",
+                to_iso8601_utc(row[9]) or "",
                 row[10],
-                row[11],
-                row[12],
-                json.dumps(row[13]) if row[13] else "",
-                row[14].isoformat() if row[14] else "",
-                row[15].isoformat() if row[15] else "",
-                row[16],
             ]
         )
 

backend/app/api/v1/dashboard.py

@@ -1,6 +1,6 @@
 """Dashboard API with caching and optimizations"""
 
-from datetime import datetime, timedelta
+from datetime import UTC, datetime, timedelta
 from fastapi import APIRouter, Depends
 from sqlalchemy import select, func, text
 from sqlalchemy.ext.asyncio import AsyncSession
@@ -13,6 +13,8 @@ from app.models.alert import Alert, AlertSeverity
 from app.models.task import CollectionTask
 from app.core.security import get_current_user
 from app.core.cache import cache
+from app.core.time import to_iso8601_utc
+
 
 # Built-in collectors info (mirrored from datasources.py)
 COLLECTOR_INFO = {
@@ -110,7 +112,7 @@ async def get_stats(
     if cached_result:
         return cached_result
 
-    today_start = datetime.utcnow().replace(hour=0, minute=0, second=0, microsecond=0)
+    today_start = datetime.now(UTC).replace(hour=0, minute=0, second=0, microsecond=0)
 
     # Count built-in collectors
     built_in_count = len(COLLECTOR_INFO)
@@ -174,7 +176,7 @@ async def get_stats(
         "active_datasources": active_datasources,
         "tasks_today": tasks_today,
         "success_rate": round(success_rate, 1),
-        "last_updated": datetime.utcnow().isoformat(),
+        "last_updated": to_iso8601_utc(datetime.now(UTC)),
         "alerts": {
             "critical": critical_alerts,
             "warning": warning_alerts,
@@ -229,10 +231,10 @@ async def get_summary(
         summary[module] = {
             "datasources": data["datasources"],
             "total_records": 0,  # Built-in don't track this in dashboard stats
-            "last_updated": datetime.utcnow().isoformat(),
+            "last_updated": to_iso8601_utc(datetime.now(UTC)),
         }
 
-    response = {"modules": summary, "last_updated": datetime.utcnow().isoformat()}
+    response = {"modules": summary, "last_updated": to_iso8601_utc(datetime.now(UTC))}
 
     cache.set(cache_key, response, expire_seconds=300)
 

backend/app/api/v1/datasource_config.py

@@ -14,6 +14,7 @@ from app.models.user import User
 from app.models.datasource_config import DataSourceConfig
 from app.core.security import get_current_user
 from app.core.cache import cache
+from app.core.time import to_iso8601_utc
 
 router = APIRouter()
 
@@ -123,8 +124,8 @@ async def list_configs(
                 "headers": c.headers,
                 "config": c.config,
                 "is_active": c.is_active,
-                "created_at": c.created_at.isoformat() if c.created_at else None,
+                "created_at": to_iso8601_utc(c.created_at),
-                "updated_at": c.updated_at.isoformat() if c.updated_at else None,
+                "updated_at": to_iso8601_utc(c.updated_at),
             }
             for c in configs
         ],
@@ -155,8 +156,8 @@ async def get_config(
         "headers": config.headers,
         "config": config.config,
         "is_active": config.is_active,
-        "created_at": config.created_at.isoformat() if config.created_at else None,
+        "created_at": to_iso8601_utc(config.created_at),
-        "updated_at": config.updated_at.isoformat() if config.updated_at else None,
+        "updated_at": to_iso8601_utc(config.updated_at),
     }
 
 
@@ -307,3 +308,40 @@ async def test_new_config(
             "error": "Connection failed",
             "message": str(e),
         }
+
+
+@router.get("/configs/all")
+async def list_all_datasources(
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    """List all data sources: YAML defaults + DB overrides"""
+    from app.core.data_sources import COLLECTOR_URL_KEYS, get_data_sources_config
+
+    config = get_data_sources_config()
+
+    db_query = await db.execute(select(DataSourceConfig))
+    db_configs = {c.name: c for c in db_query.scalars().all()}
+
+    result = []
+    for name, yaml_key in COLLECTOR_URL_KEYS.items():
+        yaml_url = config.get_yaml_url(name)
+        db_config = db_configs.get(name)
+
+        result.append(
+            {
+                "name": name,
+                "default_url": yaml_url,
+                "endpoint": db_config.endpoint if db_config else yaml_url,
+                "is_overridden": db_config is not None and db_config.endpoint != yaml_url
+                if yaml_url
+                else db_config is not None,
+                "is_active": db_config.is_active if db_config else True,
+                "source_type": db_config.source_type if db_config else "http",
+                "description": db_config.description
+                if db_config
+                else f"Data source from YAML: {yaml_key}",
+            }
+        )
+
+    return {"total": len(result), "data": result}

backend/app/api/v1/datasources.py

@@ -1,127 +1,77 @@
-from typing import List, Optional
+import asyncio
-from datetime import datetime
+from datetime import datetime, timedelta, timezone
-from fastapi import APIRouter, Depends, HTTPException, status
+from typing import Optional
-from sqlalchemy import select, func
+
+from fastapi import APIRouter, Depends, HTTPException, Query
+from sqlalchemy import func, select
 from sqlalchemy.ext.asyncio import AsyncSession
 
+from app.core.time import to_iso8601_utc
+from app.core.security import get_current_user
+from app.core.data_sources import get_data_sources_config
 from app.db.session import get_db
-from app.models.user import User
+from app.models.collected_data import CollectedData
 from app.models.datasource import DataSource
 from app.models.task import CollectionTask
-from app.models.collected_data import CollectedData
+from app.models.user import User
-from app.core.security import get_current_user
+from app.services.scheduler import get_latest_task_id_for_datasource, run_collector_now, sync_datasource_job
-from app.services.collectors.registry import collector_registry
 
 router = APIRouter()
 
-COLLECTOR_INFO = {
-    "top500": {
-        "id": 1,
-        "name": "TOP500 Supercomputers",
-        "module": "L1",
-        "priority": "P0",
-        "frequency_hours": 4,
-    },
-    "epoch_ai_gpu": {
-        "id": 2,
-        "name": "Epoch AI GPU Clusters",
-        "module": "L1",
-        "priority": "P0",
-        "frequency_hours": 6,
-    },
-    "huggingface_models": {
-        "id": 3,
-        "name": "HuggingFace Models",
-        "module": "L2",
-        "priority": "P1",
-        "frequency_hours": 12,
-    },
-    "huggingface_datasets": {
-        "id": 4,
-        "name": "HuggingFace Datasets",
-        "module": "L2",
-        "priority": "P1",
-        "frequency_hours": 12,
-    },
-    "huggingface_spaces": {
-        "id": 5,
-        "name": "HuggingFace Spaces",
-        "module": "L2",
-        "priority": "P2",
-        "frequency_hours": 24,
-    },
-    "peeringdb_ixp": {
-        "id": 6,
-        "name": "PeeringDB IXP",
-        "module": "L2",
-        "priority": "P1",
-        "frequency_hours": 24,
-    },
-    "peeringdb_network": {
-        "id": 7,
-        "name": "PeeringDB Networks",
-        "module": "L2",
-        "priority": "P2",
-        "frequency_hours": 48,
-    },
-    "peeringdb_facility": {
-        "id": 8,
-        "name": "PeeringDB Facilities",
-        "module": "L2",
-        "priority": "P2",
-        "frequency_hours": 48,
-    },
-    "telegeography_cables": {
-        "id": 9,
-        "name": "Submarine Cables",
-        "module": "L2",
-        "priority": "P1",
-        "frequency_hours": 168,
-    },
-    "telegeography_landing": {
-        "id": 10,
-        "name": "Cable Landing Points",
-        "module": "L2",
-        "priority": "P2",
-        "frequency_hours": 168,
-    },
-    "telegeography_systems": {
-        "id": 11,
-        "name": "Cable Systems",
-        "module": "L2",
-        "priority": "P2",
-        "frequency_hours": 168,
-    },
-    "arcgis_cables": {
-        "id": 15,
-        "name": "ArcGIS Submarine Cables",
-        "module": "L2",
-        "priority": "P1",
-        "frequency_hours": 168,
-    },
-    "fao_landing_points": {
-        "id": 16,
-        "name": "FAO Landing Points",
-        "module": "L2",
-        "priority": "P1",
-        "frequency_hours": 168,
-    },
-}
 
-ID_TO_COLLECTOR = {info["id"]: name for name, info in COLLECTOR_INFO.items()}
+def format_frequency_label(minutes: int) -> str:
-COLLECTOR_TO_ID = {name: info["id"] for name, info in COLLECTOR_INFO.items()}
+    if minutes % 1440 == 0:
+        return f"{minutes // 1440}d"
+    if minutes % 60 == 0:
+        return f"{minutes // 60}h"
+    return f"{minutes}m"
 
 
-def get_collector_name(source_id: str) -> Optional[str]:
+def is_due_for_collection(datasource: DataSource, now: datetime) -> bool:
+    if datasource.last_run_at is None:
+        return True
+    return datasource.last_run_at + timedelta(minutes=datasource.frequency_minutes) <= now
+
+
+async def get_datasource_record(db: AsyncSession, source_id: str) -> Optional[DataSource]:
+    datasource = None
     try:
-        numeric_id = int(source_id)
+        datasource = await db.get(DataSource, int(source_id))
-        if numeric_id in ID_TO_COLLECTOR:
-            return ID_TO_COLLECTOR[numeric_id]
     except ValueError:
         pass
-    if source_id in COLLECTOR_INFO:
+
-        return source_id
+    if datasource is not None:
-    return None
+        return datasource
+
+    result = await db.execute(
+        select(DataSource).where(
+            (DataSource.source == source_id) | (DataSource.collector_class == source_id)
+        )
+    )
+    return result.scalar_one_or_none()
+
+
+async def get_last_completed_task(db: AsyncSession, datasource_id: int) -> Optional[CollectionTask]:
+    result = await db.execute(
+        select(CollectionTask)
+        .where(CollectionTask.datasource_id == datasource_id)
+        .where(CollectionTask.completed_at.isnot(None))
+        .where(CollectionTask.status.in_(("success", "failed", "cancelled")))
+        .order_by(CollectionTask.completed_at.desc())
+        .limit(1)
+    )
+    return result.scalar_one_or_none()
+
+
+async def get_running_task(db: AsyncSession, datasource_id: int) -> Optional[CollectionTask]:
+    result = await db.execute(
+        select(CollectionTask)
+        .where(CollectionTask.datasource_id == datasource_id)
+        .where(CollectionTask.status == "running")
+        .order_by(CollectionTask.started_at.desc())
+        .limit(1)
+    )
+    return result.scalar_one_or_none()
 
 
 @router.get("")
@@ -132,80 +82,156 @@ async def list_datasources(
     current_user: User = Depends(get_current_user),
     db: AsyncSession = Depends(get_db),
 ):
-    query = select(DataSource)
+    query = select(DataSource).order_by(DataSource.module, DataSource.id)
-
-    filters = []
     if module:
-        filters.append(DataSource.module == module)
+        query = query.where(DataSource.module == module)
     if is_active is not None:
-        filters.append(DataSource.is_active == is_active)
+        query = query.where(DataSource.is_active == is_active)
     if priority:
-        filters.append(DataSource.priority == priority)
+        query = query.where(DataSource.priority == priority)
-
-    if filters:
-        query = query.where(*filters)
 
     result = await db.execute(query)
     datasources = result.scalars().all()
 
     collector_list = []
-    for name, info in COLLECTOR_INFO.items():
+    config = get_data_sources_config()
-        is_active_status = collector_registry.is_active(name)
+    for datasource in datasources:
-
+        running_task = await get_running_task(db, datasource.id)
-        running_task_query = (
+        last_task = await get_last_completed_task(db, datasource.id)
-            select(CollectionTask)
+        endpoint = await config.get_url(datasource.source, db)
-            .where(CollectionTask.datasource_id == info["id"])
+        data_count_result = await db.execute(
-            .where(CollectionTask.status == "running")
+            select(func.count(CollectedData.id)).where(CollectedData.source == datasource.source)
-            .order_by(CollectionTask.started_at.desc())
-            .limit(1)
         )
-        running_result = await db.execute(running_task_query)
-        running_task = running_result.scalar_one_or_none()
-
-        last_run_query = (
-            select(CollectionTask)
-            .where(CollectionTask.datasource_id == info["id"])
-            .where(CollectionTask.completed_at.isnot(None))
-            .order_by(CollectionTask.completed_at.desc())
-            .limit(1)
-        )
-        last_run_result = await db.execute(last_run_query)
-        last_task = last_run_result.scalar_one_or_none()
-
-        data_count_query = select(func.count(CollectedData.id)).where(CollectedData.source == name)
-        data_count_result = await db.execute(data_count_query)
         data_count = data_count_result.scalar() or 0
 
-        last_run = None
+        last_run_at = datasource.last_run_at or (last_task.completed_at if last_task else None)
-        if last_task and last_task.completed_at and data_count > 0:
+        last_run = to_iso8601_utc(last_run_at)
-            last_run = last_task.completed_at.strftime("%Y-%m-%d %H:%M")
+        last_status = datasource.last_status or (last_task.status if last_task else None)
 
         collector_list.append(
             {
-                "id": info["id"],
+                "id": datasource.id,
-                "name": info["name"],
+                "name": datasource.name,
-                "module": info["module"],
+                "module": datasource.module,
-                "priority": info["priority"],
+                "priority": datasource.priority,
-                "frequency": f"{info['frequency_hours']}h",
+                "frequency": format_frequency_label(datasource.frequency_minutes),
-                "is_active": is_active_status,
+                "frequency_minutes": datasource.frequency_minutes,
-                "collector_class": name,
+                "is_active": datasource.is_active,
+                "collector_class": datasource.collector_class,
+                "endpoint": endpoint,
                 "last_run": last_run,
+                "last_run_at": to_iso8601_utc(last_run_at),
+                "last_status": last_status,
+                "last_records_processed": last_task.records_processed if last_task else None,
+                "data_count": data_count,
                 "is_running": running_task is not None,
                 "task_id": running_task.id if running_task else None,
                 "progress": running_task.progress if running_task else None,
+                "phase": running_task.phase if running_task else None,
                 "records_processed": running_task.records_processed if running_task else None,
                 "total_records": running_task.total_records if running_task else None,
             }
         )
 
-    if module:
+    return {"total": len(collector_list), "data": collector_list}
-        collector_list = [c for c in collector_list if c["module"] == module]
+
-    if priority:
+
-        collector_list = [c for c in collector_list if c["priority"] == priority]
+@router.post("/trigger-all")
+async def trigger_all_datasources(
+    force: bool = Query(False),
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    result = await db.execute(
+        select(DataSource)
+        .where(DataSource.is_active == True)
+        .order_by(DataSource.module, DataSource.id)
+    )
+    datasources = result.scalars().all()
+
+    if not datasources:
+        return {
+            "status": "noop",
+            "message": "No active data sources to trigger",
+            "triggered": [],
+            "skipped": [],
+            "failed": [],
+        }
+
+    previous_task_ids: dict[int, Optional[int]] = {}
+    triggered_sources: list[dict] = []
+    skipped_sources: list[dict] = []
+    failed_sources: list[dict] = []
+    now = datetime.now(timezone.utc)
+
+    for datasource in datasources:
+        running_task = await get_running_task(db, datasource.id)
+        if running_task is not None:
+            skipped_sources.append(
+                {
+                    "id": datasource.id,
+                    "source": datasource.source,
+                    "name": datasource.name,
+                    "reason": "already_running",
+                    "task_id": running_task.id,
+                }
+            )
+            continue
+
+        if not force and not is_due_for_collection(datasource, now):
+            skipped_sources.append(
+                {
+                    "id": datasource.id,
+                    "source": datasource.source,
+                    "name": datasource.name,
+                    "reason": "within_frequency_window",
+                    "last_run_at": to_iso8601_utc(datasource.last_run_at),
+                    "next_run_at": to_iso8601_utc(
+                        datasource.last_run_at + timedelta(minutes=datasource.frequency_minutes)
+                    ),
+                }
+            )
+            continue
+
+        previous_task_ids[datasource.id] = await get_latest_task_id_for_datasource(datasource.id)
+        success = run_collector_now(datasource.source)
+        if not success:
+            failed_sources.append(
+                {
+                    "id": datasource.id,
+                    "source": datasource.source,
+                    "name": datasource.name,
+                    "reason": "trigger_failed",
+                }
+            )
+            continue
+
+        triggered_sources.append(
+            {
+                "id": datasource.id,
+                "source": datasource.source,
+                "name": datasource.name,
+                "task_id": None,
+            }
+        )
+
+    for _ in range(20):
+        await asyncio.sleep(0.1)
+        pending = [item for item in triggered_sources if item["task_id"] is None]
+        if not pending:
+            break
+        for item in pending:
+            task_id = await get_latest_task_id_for_datasource(item["id"])
+            if task_id is not None and task_id != previous_task_ids.get(item["id"]):
+                item["task_id"] = task_id
 
     return {
-        "total": len(collector_list),
+        "status": "triggered" if triggered_sources else "partial",
-        "data": collector_list,
+        "message": f"Triggered {len(triggered_sources)} data sources",
+        "force": force,
+        "triggered": triggered_sources,
+        "skipped": skipped_sources,
+        "failed": failed_sources,
     }
 
 
@@ -215,19 +241,24 @@ async def get_datasource(
     current_user: User = Depends(get_current_user),
     db: AsyncSession = Depends(get_db),
 ):
-    collector_name = get_collector_name(source_id)
+    datasource = await get_datasource_record(db, source_id)
-    if not collector_name:
+    if not datasource:
         raise HTTPException(status_code=404, detail="Data source not found")
 
-    info = COLLECTOR_INFO[collector_name]
+    config = get_data_sources_config()
+    endpoint = await config.get_url(datasource.source, db)
+
     return {
-        "id": info["id"],
+        "id": datasource.id,
-        "name": info["name"],
+        "name": datasource.name,
-        "module": info["module"],
+        "module": datasource.module,
-        "priority": info["priority"],
+        "priority": datasource.priority,
-        "frequency": f"{info['frequency_hours']}h",
+        "frequency": format_frequency_label(datasource.frequency_minutes),
-        "collector_class": collector_name,
+        "frequency_minutes": datasource.frequency_minutes,
-        "is_active": collector_registry.is_active(collector_name),
+        "collector_class": datasource.collector_class,
+        "source": datasource.source,
+        "endpoint": endpoint,
+        "is_active": datasource.is_active,
     }
 
 
@@ -235,24 +266,32 @@ async def get_datasource(
 async def enable_datasource(
     source_id: str,
     current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
 ):
-    collector_name = get_collector_name(source_id)
+    datasource = await get_datasource_record(db, source_id)
-    if not collector_name:
+    if not datasource:
         raise HTTPException(status_code=404, detail="Data source not found")
-    collector_registry.set_active(collector_name, True)
+
-    return {"status": "enabled", "source_id": source_id}
+    datasource.is_active = True
+    await db.commit()
+    await sync_datasource_job(datasource.id)
+    return {"status": "enabled", "source_id": datasource.id}
 
 
 @router.post("/{source_id}/disable")
 async def disable_datasource(
     source_id: str,
     current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
 ):
-    collector_name = get_collector_name(source_id)
+    datasource = await get_datasource_record(db, source_id)
-    if not collector_name:
+    if not datasource:
         raise HTTPException(status_code=404, detail="Data source not found")
-    collector_registry.set_active(collector_name, False)
+
-    return {"status": "disabled", "source_id": source_id}
+    datasource.is_active = False
+    await db.commit()
+    await sync_datasource_job(datasource.id)
+    return {"status": "disabled", "source_id": datasource.id}
 
 
 @router.get("/{source_id}/stats")
@@ -261,26 +300,19 @@ async def get_datasource_stats(
     current_user: User = Depends(get_current_user),
     db: AsyncSession = Depends(get_db),
 ):
-    collector_name = get_collector_name(source_id)
+    datasource = await get_datasource_record(db, source_id)
-    if not collector_name:
+    if not datasource:
         raise HTTPException(status_code=404, detail="Data source not found")
 
-    info = COLLECTOR_INFO[collector_name]
+    result = await db.execute(
-    source_name = info["name"]
+        select(func.count(CollectedData.id)).where(CollectedData.source == datasource.source)
-
+    )
-    query = select(func.count(CollectedData.id)).where(CollectedData.source == collector_name)
-    result = await db.execute(query)
-    total = result.scalar() or 0
-
-    if total == 0:
-        query = select(func.count(CollectedData.id)).where(CollectedData.source == source_name)
-        result = await db.execute(query)
     total = result.scalar() or 0
 
     return {
-        "source_id": source_id,
+        "source_id": datasource.id,
-        "collector_name": collector_name,
+        "collector_name": datasource.collector_class,
-        "name": info["name"],
+        "name": datasource.name,
         "total_records": total,
     }
 
@@ -289,30 +321,36 @@ async def get_datasource_stats(
 async def trigger_datasource(
     source_id: str,
     current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
 ):
-    collector_name = get_collector_name(source_id)
+    datasource = await get_datasource_record(db, source_id)
-    if not collector_name:
+    if not datasource:
         raise HTTPException(status_code=404, detail="Data source not found")
 
-    from app.services.scheduler import run_collector_now
+    if not datasource.is_active:
-
-    if not collector_registry.is_active(collector_name):
         raise HTTPException(status_code=400, detail="Data source is disabled")
 
-    success = run_collector_now(collector_name)
+    previous_task_id = await get_latest_task_id_for_datasource(datasource.id)
+    success = run_collector_now(datasource.source)
+    if not success:
+        raise HTTPException(status_code=500, detail=f"Failed to trigger collector '{datasource.source}'")
+
+    task_id = None
+    for _ in range(20):
+        await asyncio.sleep(0.1)
+        task_id = await get_latest_task_id_for_datasource(datasource.id)
+        if task_id is not None and task_id != previous_task_id:
+            break
+    if task_id == previous_task_id:
+        task_id = None
 
-    if success:
     return {
         "status": "triggered",
-            "source_id": source_id,
+        "source_id": datasource.id,
-            "collector_name": collector_name,
+        "task_id": task_id,
-            "message": f"Collector '{collector_name}' has been triggered",
+        "collector_name": datasource.source,
+        "message": f"Collector '{datasource.source}' has been triggered",
     }
-    else:
-        raise HTTPException(
-            status_code=500,
-            detail=f"Failed to trigger collector '{collector_name}'",
-        )
 
 
 @router.delete("/{source_id}/data")
@@ -321,39 +359,25 @@ async def clear_datasource_data(
     current_user: User = Depends(get_current_user),
     db: AsyncSession = Depends(get_db),
 ):
-    collector_name = get_collector_name(source_id)
+    datasource = await get_datasource_record(db, source_id)
-    if not collector_name:
+    if not datasource:
         raise HTTPException(status_code=404, detail="Data source not found")
 
-    info = COLLECTOR_INFO[collector_name]
+    result = await db.execute(
-    source_name = info["name"]
+        select(func.count(CollectedData.id)).where(CollectedData.source == datasource.source)
-
+    )
-    query = select(func.count(CollectedData.id)).where(CollectedData.source == collector_name)
-    result = await db.execute(query)
     count = result.scalar() or 0
 
     if count == 0:
-        query = select(func.count(CollectedData.id)).where(CollectedData.source == source_name)
+        return {"status": "success", "message": "No data to clear", "deleted_count": 0}
-        result = await db.execute(query)
-        count = result.scalar() or 0
-        delete_source = source_name
-    else:
-        delete_source = collector_name
 
-    if count == 0:
+    delete_query = CollectedData.__table__.delete().where(CollectedData.source == datasource.source)
-        return {
-            "status": "success",
-            "message": "No data to clear",
-            "deleted_count": 0,
-        }
-
-    delete_query = CollectedData.__table__.delete().where(CollectedData.source == delete_source)
     await db.execute(delete_query)
     await db.commit()
 
     return {
         "status": "success",
-        "message": f"Cleared {count} records for data source '{info['name']}'",
+        "message": f"Cleared {count} records for data source '{datasource.name}'",
         "deleted_count": count,
     }
 
@@ -361,32 +385,29 @@ async def clear_datasource_data(
 @router.get("/{source_id}/task-status")
 async def get_task_status(
     source_id: str,
+    task_id: Optional[int] = None,
     db: AsyncSession = Depends(get_db),
 ):
-    collector_name = get_collector_name(source_id)
+    datasource = await get_datasource_record(db, source_id)
-    if not collector_name:
+    if not datasource:
         raise HTTPException(status_code=404, detail="Data source not found")
 
-    info = COLLECTOR_INFO[collector_name]
+    if task_id is not None:
+        task = await db.get(CollectionTask, task_id)
+        if not task or task.datasource_id != datasource.id:
+            raise HTTPException(status_code=404, detail="Task not found")
+    else:
+        task = await get_running_task(db, datasource.id)
 
-    running_task_query = (
+    if not task:
-        select(CollectionTask)
+        return {"is_running": False, "task_id": None, "progress": None, "phase": None, "status": "idle"}
-        .where(CollectionTask.datasource_id == info["id"])
-        .where(CollectionTask.status == "running")
-        .order_by(CollectionTask.started_at.desc())
-        .limit(1)
-    )
-    running_result = await db.execute(running_task_query)
-    running_task = running_result.scalar_one_or_none()
-
-    if not running_task:
-        return {"is_running": False, "task_id": None, "progress": None}
 
     return {
-        "is_running": True,
+        "is_running": task.status == "running",
-        "task_id": running_task.id,
+        "task_id": task.id,
-        "progress": running_task.progress,
+        "progress": task.progress,
-        "records_processed": running_task.records_processed,
+        "phase": task.phase,
-        "total_records": running_task.total_records,
+        "records_processed": task.records_processed,
-        "status": running_task.status,
+        "total_records": task.total_records,
+        "status": task.status,
     }

backend/app/api/v1/settings.py

@@ -1,13 +1,22 @@
+from datetime import UTC, datetime
 from typing import Optional
-from fastapi import APIRouter, Depends, HTTPException
-from pydantic import BaseModel, EmailStr
 
-from app.models.user import User
+from fastapi import APIRouter, Depends, HTTPException
+from pydantic import BaseModel, EmailStr, Field
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
+
 from app.core.security import get_current_user
+from app.core.time import to_iso8601_utc
+from app.db.session import get_db
+from app.models.datasource import DataSource
+from app.models.system_setting import SystemSetting
+from app.models.user import User
+from app.services.scheduler import sync_datasource_job
 
 router = APIRouter()
 
-default_settings = {
+DEFAULT_SETTINGS = {
     "system": {
         "system_name": "智能星球",
         "refresh_interval": 60,
@@ -29,17 +38,13 @@ default_settings = {
     },
 }
 
-system_settings = default_settings["system"].copy()
-notification_settings = default_settings["notifications"].copy()
-security_settings = default_settings["security"].copy()
-
 
 class SystemSettingsUpdate(BaseModel):
     system_name: str = "智能星球"
-    refresh_interval: int = 60
+    refresh_interval: int = Field(default=60, ge=10, le=3600)
     auto_refresh: bool = True
-    data_retention_days: int = 30
+    data_retention_days: int = Field(default=30, ge=1, le=3650)
-    max_concurrent_tasks: int = 5
+    max_concurrent_tasks: int = Field(default=5, ge=1, le=50)
 
 
 class NotificationSettingsUpdate(BaseModel):
@@ -51,60 +56,166 @@ class NotificationSettingsUpdate(BaseModel):
 
 
 class SecuritySettingsUpdate(BaseModel):
-    session_timeout: int = 60
+    session_timeout: int = Field(default=60, ge=5, le=1440)
-    max_login_attempts: int = 5
+    max_login_attempts: int = Field(default=5, ge=1, le=20)
-    password_policy: str = "medium"
+    password_policy: str = Field(default="medium")
+
+
+class CollectorSettingsUpdate(BaseModel):
+    is_active: bool
+    priority: str = Field(default="P1")
+    frequency_minutes: int = Field(default=60, ge=1, le=10080)
+
+
+def merge_with_defaults(category: str, payload: Optional[dict]) -> dict:
+    merged = DEFAULT_SETTINGS[category].copy()
+    if payload:
+        merged.update(payload)
+    return merged
+
+
+async def get_setting_record(db: AsyncSession, category: str) -> Optional[SystemSetting]:
+    result = await db.execute(select(SystemSetting).where(SystemSetting.category == category))
+    return result.scalar_one_or_none()
+
+
+async def get_setting_payload(db: AsyncSession, category: str) -> dict:
+    record = await get_setting_record(db, category)
+    return merge_with_defaults(category, record.payload if record else None)
+
+
+async def save_setting_payload(db: AsyncSession, category: str, payload: dict) -> dict:
+    record = await get_setting_record(db, category)
+    if record is None:
+        record = SystemSetting(category=category, payload=payload)
+        db.add(record)
+    else:
+        record.payload = payload
+
+    await db.commit()
+    await db.refresh(record)
+    return merge_with_defaults(category, record.payload)
+
+
+def format_frequency_label(minutes: int) -> str:
+    if minutes % 1440 == 0:
+        return f"{minutes // 1440}d"
+    if minutes % 60 == 0:
+        return f"{minutes // 60}h"
+    return f"{minutes}m"
+
+
+def serialize_collector(datasource: DataSource) -> dict:
+    return {
+        "id": datasource.id,
+        "name": datasource.name,
+        "source": datasource.source,
+        "module": datasource.module,
+        "priority": datasource.priority,
+        "frequency_minutes": datasource.frequency_minutes,
+        "frequency": format_frequency_label(datasource.frequency_minutes),
+        "is_active": datasource.is_active,
+        "last_run_at": to_iso8601_utc(datasource.last_run_at),
+        "last_status": datasource.last_status,
+        "next_run_at": to_iso8601_utc(datasource.next_run_at),
+    }
 
 
 @router.get("/system")
-async def get_system_settings(current_user: User = Depends(get_current_user)):
+async def get_system_settings(
-    return {"system": system_settings}
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    return {"system": await get_setting_payload(db, "system")}
 
 
 @router.put("/system")
 async def update_system_settings(
     settings: SystemSettingsUpdate,
     current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
 ):
-    global system_settings
+    payload = await save_setting_payload(db, "system", settings.model_dump())
-    system_settings = settings.model_dump()
+    return {"status": "updated", "system": payload}
-    return {"status": "updated", "system": system_settings}
 
 
 @router.get("/notifications")
-async def get_notification_settings(current_user: User = Depends(get_current_user)):
+async def get_notification_settings(
-    return {"notifications": notification_settings}
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    return {"notifications": await get_setting_payload(db, "notifications")}
 
 
 @router.put("/notifications")
 async def update_notification_settings(
     settings: NotificationSettingsUpdate,
     current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
 ):
-    global notification_settings
+    payload = await save_setting_payload(db, "notifications", settings.model_dump())
-    notification_settings = settings.model_dump()
+    return {"status": "updated", "notifications": payload}
-    return {"status": "updated", "notifications": notification_settings}
 
 
 @router.get("/security")
-async def get_security_settings(current_user: User = Depends(get_current_user)):
+async def get_security_settings(
-    return {"security": security_settings}
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    return {"security": await get_setting_payload(db, "security")}
 
 
 @router.put("/security")
 async def update_security_settings(
     settings: SecuritySettingsUpdate,
     current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
 ):
-    global security_settings
+    payload = await save_setting_payload(db, "security", settings.model_dump())
-    security_settings = settings.model_dump()
+    return {"status": "updated", "security": payload}
-    return {"status": "updated", "security": security_settings}
+
+
+@router.get("/collectors")
+async def get_collector_settings(
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    result = await db.execute(select(DataSource).order_by(DataSource.module, DataSource.id))
+    datasources = result.scalars().all()
+    return {"collectors": [serialize_collector(datasource) for datasource in datasources]}
+
+
+@router.put("/collectors/{datasource_id}")
+async def update_collector_settings(
+    datasource_id: int,
+    settings: CollectorSettingsUpdate,
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    datasource = await db.get(DataSource, datasource_id)
+    if not datasource:
+        raise HTTPException(status_code=404, detail="Data source not found")
+
+    datasource.is_active = settings.is_active
+    datasource.priority = settings.priority
+    datasource.frequency_minutes = settings.frequency_minutes
+    await db.commit()
+    await db.refresh(datasource)
+    await sync_datasource_job(datasource.id)
+    return {"status": "updated", "collector": serialize_collector(datasource)}
 
 
 @router.get("")
-async def get_all_settings(current_user: User = Depends(get_current_user)):
+async def get_all_settings(
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    result = await db.execute(select(DataSource).order_by(DataSource.module, DataSource.id))
+    datasources = result.scalars().all()
     return {
-        "system": system_settings,
+        "system": await get_setting_payload(db, "system"),
-        "notifications": notification_settings,
+        "notifications": await get_setting_payload(db, "notifications"),
-        "security": security_settings,
+        "security": await get_setting_payload(db, "security"),
+        "collectors": [serialize_collector(datasource) for datasource in datasources],
+        "generated_at": to_iso8601_utc(datetime.now(UTC)),
     }

backend/app/api/v1/tasks.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import UTC, datetime
 from typing import Optional
 
 from fastapi import APIRouter, Depends, HTTPException, status
@@ -8,8 +8,10 @@ from sqlalchemy import text
 from app.db.session import get_db
 from app.models.user import User
 from app.core.security import get_current_user
+from app.core.time import to_iso8601_utc
 from app.services.collectors.registry import collector_registry
 
+
 router = APIRouter()
 
 
@@ -60,8 +62,8 @@ async def list_tasks(
                 "datasource_id": t[1],
                 "datasource_name": t[2],
                 "status": t[3],
-                "started_at": t[4].isoformat() if t[4] else None,
+                "started_at": to_iso8601_utc(t[4]),
-                "completed_at": t[5].isoformat() if t[5] else None,
+                "completed_at": to_iso8601_utc(t[5]),
                 "records_processed": t[6],
                 "error_message": t[7],
             }
@@ -99,8 +101,8 @@ async def get_task(
         "datasource_id": task[1],
         "datasource_name": task[2],
         "status": task[3],
-        "started_at": task[4].isoformat() if task[4] else None,
+        "started_at": to_iso8601_utc(task[4]),
-        "completed_at": task[5].isoformat() if task[5] else None,
+        "completed_at": to_iso8601_utc(task[5]),
         "records_processed": task[6],
         "error_message": task[7],
     }
@@ -146,8 +148,8 @@ async def trigger_collection(
             "status": result.get("status", "unknown"),
             "records_processed": result.get("records_processed", 0),
             "error_message": result.get("error"),
-            "started_at": datetime.utcnow(),
+            "started_at": datetime.now(UTC),
-            "completed_at": datetime.utcnow(),
+            "completed_at": datetime.now(UTC),
         },
     )
 

backend/app/api/v1/visualization.py

@@ -1,17 +1,30 @@
-"""Visualization API - GeoJSON endpoints for 3D Earth display"""
+"""Visualization API - GeoJSON endpoints for 3D Earth display
 
-from fastapi import APIRouter, HTTPException, Depends
+Unified API for all visualization data sources.
+Returns GeoJSON format compatible with Three.js, CesiumJS, and Unreal Cesium.
+"""
+
+from datetime import UTC, datetime
+from fastapi import APIRouter, HTTPException, Depends, Query
 from sqlalchemy.ext.asyncio import AsyncSession
-from sqlalchemy import select
+from sqlalchemy import select, func
 from typing import List, Dict, Any, Optional
 
+from app.core.collected_data_fields import get_record_field
+from app.core.satellite_tle import build_tle_lines_from_elements
+from app.core.time import to_iso8601_utc
 from app.db.session import get_db
+from app.models.bgp_anomaly import BGPAnomaly
 from app.models.collected_data import CollectedData
 from app.services.cable_graph import build_graph_from_data, CableGraph
+from app.services.collectors.bgp_common import RIPE_RIS_COLLECTOR_COORDS
 
 router = APIRouter()
 
 
+# ============== Converter Functions ==============
+
+
 def convert_cable_to_geojson(records: List[CollectedData]) -> Dict[str, Any]:
     """Convert cable records to GeoJSON FeatureCollection"""
     features = []
@@ -66,6 +79,7 @@ def convert_cable_to_geojson(records: List[CollectedData]) -> Dict[str, Any]:
                 "geometry": {"type": "MultiLineString", "coordinates": all_lines},
                 "properties": {
                     "id": record.id,
+                    "cable_id": record.name,
                     "source_id": record.source_id,
                     "Name": record.name,
                     "name": record.name,
@@ -74,9 +88,9 @@ def convert_cable_to_geojson(records: List[CollectedData]) -> Dict[str, Any]:
                     "rfs": metadata.get("rfs"),
                     "RFS": metadata.get("rfs"),
                     "status": metadata.get("status", "active"),
-                    "length": record.value,
+                    "length": get_record_field(record, "value"),
-                    "length_km": record.value,
+                    "length_km": get_record_field(record, "value"),
-                    "SHAPE__Length": record.value,
+                    "SHAPE__Length": get_record_field(record, "value"),
                     "url": metadata.get("url"),
                     "color": metadata.get("color"),
                     "year": metadata.get("year"),
@@ -87,14 +101,15 @@ def convert_cable_to_geojson(records: List[CollectedData]) -> Dict[str, Any]:
     return {"type": "FeatureCollection", "features": features}
 
 
-def convert_landing_point_to_geojson(records: List[CollectedData]) -> Dict[str, Any]:
+def convert_landing_point_to_geojson(records: List[CollectedData], city_to_cable_ids_map: Dict[int, List[int]] = None, cable_id_to_name_map: Dict[int, str] = None) -> Dict[str, Any]:
-    """Convert landing point records to GeoJSON FeatureCollection"""
     features = []
     
     for record in records:
         try:
-            lat = float(record.latitude) if record.latitude else None
+            latitude = get_record_field(record, "latitude")
-            lon = float(record.longitude) if record.longitude else None
+            longitude = get_record_field(record, "longitude")
+            lat = float(latitude) if latitude else None
+            lon = float(longitude) if longitude else None
         except (ValueError, TypeError):
             continue
         
@@ -102,18 +117,84 @@ def convert_landing_point_to_geojson(records: List[CollectedData]) -> Dict[str,
             continue
         
         metadata = record.extra_data or {}
+        city_id = metadata.get("city_id")
+        
+        props = {
+            "id": record.id,
+            "source_id": record.source_id,
+            "name": record.name,
+            "country": get_record_field(record, "country"),
+            "city": get_record_field(record, "city"),
+            "is_tbd": metadata.get("is_tbd", False),
+        }
+        
+        cable_names = []
+        if city_to_cable_ids_map and city_id in city_to_cable_ids_map:
+            for cable_id in city_to_cable_ids_map[city_id]:
+                if cable_id_to_name_map and cable_id in cable_id_to_name_map:
+                    cable_names.append(cable_id_to_name_map[cable_id])
+        
+        if cable_names:
+            props["cable_names"] = cable_names
         
         features.append(
             {
                 "type": "Feature",
                 "geometry": {"type": "Point", "coordinates": [lon, lat]},
+                "properties": props,
+            }
+        )
+    
+    return {"type": "FeatureCollection", "features": features}
+
+
+def convert_satellite_to_geojson(records: List[CollectedData]) -> Dict[str, Any]:
+    """Convert satellite TLE records to GeoJSON"""
+    features = []
+
+    for record in records:
+        metadata = record.extra_data or {}
+        norad_id = metadata.get("norad_cat_id")
+
+        if not norad_id:
+            continue
+
+        tle_line1 = metadata.get("tle_line1")
+        tle_line2 = metadata.get("tle_line2")
+        if not tle_line1 or not tle_line2:
+            tle_line1, tle_line2 = build_tle_lines_from_elements(
+                norad_cat_id=norad_id,
+                epoch=metadata.get("epoch"),
+                inclination=metadata.get("inclination"),
+                raan=metadata.get("raan"),
+                eccentricity=metadata.get("eccentricity"),
+                arg_of_perigee=metadata.get("arg_of_perigee"),
+                mean_anomaly=metadata.get("mean_anomaly"),
+                mean_motion=metadata.get("mean_motion"),
+            )
+
+        features.append(
+            {
+                "type": "Feature",
+                "id": norad_id,
+                "geometry": {"type": "Point", "coordinates": [0, 0, 0]},
                 "properties": {
                     "id": record.id,
-                    "source_id": record.source_id,
+                    "norad_cat_id": norad_id,
                     "name": record.name,
-                    "country": record.country,
+                    "international_designator": metadata.get("international_designator"),
-                    "city": record.city,
+                    "epoch": metadata.get("epoch"),
-                    "is_tbd": metadata.get("is_tbd", False),
+                    "inclination": metadata.get("inclination"),
+                    "raan": metadata.get("raan"),
+                    "eccentricity": metadata.get("eccentricity"),
+                    "arg_of_perigee": metadata.get("arg_of_perigee"),
+                    "mean_anomaly": metadata.get("mean_anomaly"),
+                    "mean_motion": metadata.get("mean_motion"),
+                    "bstar": metadata.get("bstar"),
+                    "classification_type": metadata.get("classification_type"),
+                    "tle_line1": tle_line1,
+                    "tle_line2": tle_line2,
+                    "data_type": "satellite_tle",
                 },
             }
         )
@@ -121,6 +202,158 @@ def convert_landing_point_to_geojson(records: List[CollectedData]) -> Dict[str,
     return {"type": "FeatureCollection", "features": features}
 
 
+def convert_supercomputer_to_geojson(records: List[CollectedData]) -> Dict[str, Any]:
+    """Convert TOP500 supercomputer records to GeoJSON"""
+    features = []
+
+    for record in records:
+        try:
+            latitude = get_record_field(record, "latitude")
+            longitude = get_record_field(record, "longitude")
+            lat = float(latitude) if latitude and latitude != "0.0" else None
+            lon = (
+                float(longitude) if longitude and longitude != "0.0" else None
+            )
+        except (ValueError, TypeError):
+            lat, lon = None, None
+
+        metadata = record.extra_data or {}
+
+        features.append(
+            {
+                "type": "Feature",
+                "id": record.id,
+                "geometry": {"type": "Point", "coordinates": [lon or 0, lat or 0]},
+                "properties": {
+                    "id": record.id,
+                    "name": record.name,
+                    "rank": metadata.get("rank"),
+                    "r_max": get_record_field(record, "rmax"),
+                    "r_peak": get_record_field(record, "rpeak"),
+                    "cores": get_record_field(record, "cores"),
+                    "power": get_record_field(record, "power"),
+                    "country": get_record_field(record, "country"),
+                    "city": get_record_field(record, "city"),
+                    "data_type": "supercomputer",
+                },
+            }
+        )
+
+    return {"type": "FeatureCollection", "features": features}
+
+
+def convert_gpu_cluster_to_geojson(records: List[CollectedData]) -> Dict[str, Any]:
+    """Convert GPU cluster records to GeoJSON"""
+    features = []
+
+    for record in records:
+        try:
+            latitude = get_record_field(record, "latitude")
+            longitude = get_record_field(record, "longitude")
+            lat = float(latitude) if latitude else None
+            lon = float(longitude) if longitude else None
+        except (ValueError, TypeError):
+            lat, lon = None, None
+
+        metadata = record.extra_data or {}
+
+        features.append(
+            {
+                "type": "Feature",
+                "id": record.id,
+                "geometry": {"type": "Point", "coordinates": [lon or 0, lat or 0]},
+                "properties": {
+                    "id": record.id,
+                    "name": record.name,
+                    "country": get_record_field(record, "country"),
+                    "city": get_record_field(record, "city"),
+                    "metadata": metadata,
+                    "data_type": "gpu_cluster",
+                },
+            }
+        )
+
+    return {"type": "FeatureCollection", "features": features}
+
+
+def convert_bgp_anomalies_to_geojson(records: List[BGPAnomaly]) -> Dict[str, Any]:
+    features = []
+
+    for record in records:
+        evidence = record.evidence or {}
+        collectors = evidence.get("collectors") or record.peer_scope or []
+        collector = collectors[0] if collectors else None
+        location = None
+        if collector:
+            location = RIPE_RIS_COLLECTOR_COORDS.get(str(collector))
+
+        if location is None:
+            nested = evidence.get("events") or []
+            for item in nested:
+                collector_name = (item or {}).get("collector")
+                if collector_name and collector_name in RIPE_RIS_COLLECTOR_COORDS:
+                    location = RIPE_RIS_COLLECTOR_COORDS[collector_name]
+                    collector = collector_name
+                    break
+
+        if location is None:
+            continue
+
+        features.append(
+            {
+                "type": "Feature",
+                "geometry": {
+                    "type": "Point",
+                    "coordinates": [location["longitude"], location["latitude"]],
+                },
+                "properties": {
+                    "id": record.id,
+                    "collector": collector,
+                    "city": location.get("city"),
+                    "country": location.get("country"),
+                    "source": record.source,
+                    "anomaly_type": record.anomaly_type,
+                    "severity": record.severity,
+                    "status": record.status,
+                    "prefix": record.prefix,
+                    "origin_asn": record.origin_asn,
+                    "new_origin_asn": record.new_origin_asn,
+                    "confidence": record.confidence,
+                    "summary": record.summary,
+                    "created_at": to_iso8601_utc(record.created_at),
+                },
+            }
+        )
+
+    return {"type": "FeatureCollection", "features": features}
+
+
+def convert_bgp_collectors_to_geojson() -> Dict[str, Any]:
+    features = []
+
+    for collector, location in sorted(RIPE_RIS_COLLECTOR_COORDS.items()):
+        features.append(
+            {
+                "type": "Feature",
+                "geometry": {
+                    "type": "Point",
+                    "coordinates": [location["longitude"], location["latitude"]],
+                },
+                "properties": {
+                    "collector": collector,
+                    "city": location.get("city"),
+                    "country": location.get("country"),
+                    "status": "online",
+                },
+            }
+        )
+
+    return {"type": "FeatureCollection", "features": features}
+
+
+# ============== API Endpoints ==============
+
+
 @router.get("/geo/cables")
 async def get_cables_geojson(db: AsyncSession = Depends(get_db)):
     """获取海底电缆 GeoJSON 数据 (LineString)"""
@@ -144,19 +377,45 @@ async def get_cables_geojson(db: AsyncSession = Depends(get_db)):
 
 @router.get("/geo/landing-points")
 async def get_landing_points_geojson(db: AsyncSession = Depends(get_db)):
-    """获取登陆点 GeoJSON 数据 (Point)"""
     try:
-        stmt = select(CollectedData).where(CollectedData.source == "fao_landing_points")
+        landing_stmt = select(CollectedData).where(CollectedData.source == "arcgis_landing_points")
-        result = await db.execute(stmt)
+        landing_result = await db.execute(landing_stmt)
-        records = result.scalars().all()
+        records = landing_result.scalars().all()
+        
+        relation_stmt = select(CollectedData).where(CollectedData.source == "arcgis_cable_landing_relation")
+        relation_result = await db.execute(relation_stmt)
+        relation_records = relation_result.scalars().all()
+        
+        cable_stmt = select(CollectedData).where(CollectedData.source == "arcgis_cables")
+        cable_result = await db.execute(cable_stmt)
+        cable_records = cable_result.scalars().all()
+        
+        city_to_cable_ids_map = {}
+        for rel in relation_records:
+            if rel.extra_data:
+                city_id = rel.extra_data.get("city_id")
+                cable_id = rel.extra_data.get("cable_id")
+                if city_id is not None and cable_id is not None:
+                    if city_id not in city_to_cable_ids_map:
+                        city_to_cable_ids_map[city_id] = []
+                    if cable_id not in city_to_cable_ids_map[city_id]:
+                        city_to_cable_ids_map[city_id].append(cable_id)
+        
+        cable_id_to_name_map = {}
+        for cable in cable_records:
+            if cable.extra_data:
+                cable_id = cable.extra_data.get("cable_id")
+                cable_name = cable.name
+                if cable_id and cable_name:
+                    cable_id_to_name_map[cable_id] = cable_name
         
         if not records:
             raise HTTPException(
                 status_code=404,
-                detail="No landing point data found. Please run the fao_landing_points collector first.",
+                detail="No landing point data found. Please run the arcgis_landing_points collector first.",
             )
         
-        return convert_landing_point_to_geojson(records)
+        return convert_landing_point_to_geojson(records, city_to_cable_ids_map, cable_id_to_name_map)
     except HTTPException:
         raise
     except Exception as e:
@@ -165,22 +424,44 @@ async def get_landing_points_geojson(db: AsyncSession = Depends(get_db)):
 
 @router.get("/geo/all")
 async def get_all_geojson(db: AsyncSession = Depends(get_db)):
-    """获取所有可视化数据 (电缆 + 登陆点)"""
     cables_stmt = select(CollectedData).where(CollectedData.source == "arcgis_cables")
     cables_result = await db.execute(cables_stmt)
     cables_records = cables_result.scalars().all()
 
-    points_stmt = select(CollectedData).where(CollectedData.source == "fao_landing_points")
+    points_stmt = select(CollectedData).where(CollectedData.source == "arcgis_landing_points")
     points_result = await db.execute(points_stmt)
     points_records = points_result.scalars().all()
     
+    relation_stmt = select(CollectedData).where(CollectedData.source == "arcgis_cable_landing_relation")
+    relation_result = await db.execute(relation_stmt)
+    relation_records = relation_result.scalars().all()
+    
+    city_to_cable_ids_map = {}
+    for rel in relation_records:
+        if rel.extra_data:
+            city_id = rel.extra_data.get("city_id")
+            cable_id = rel.extra_data.get("cable_id")
+            if city_id is not None and cable_id is not None:
+                if city_id not in city_to_cable_ids_map:
+                    city_to_cable_ids_map[city_id] = []
+                if cable_id not in city_to_cable_ids_map[city_id]:
+                    city_to_cable_ids_map[city_id].append(cable_id)
+    
+    cable_id_to_name_map = {}
+    for cable in cables_records:
+        if cable.extra_data:
+            cable_id = cable.extra_data.get("cable_id")
+            cable_name = cable.name
+            if cable_id and cable_name:
+                cable_id_to_name_map[cable_id] = cable_name
+
     cables = (
         convert_cable_to_geojson(cables_records)
         if cables_records
         else {"type": "FeatureCollection", "features": []}
     )
     points = (
-        convert_landing_point_to_geojson(points_records)
+        convert_landing_point_to_geojson(points_records, city_to_cable_ids_map, cable_id_to_name_map)
         if points_records
         else {"type": "FeatureCollection", "features": []}
     )
@@ -195,6 +476,208 @@ async def get_all_geojson(db: AsyncSession = Depends(get_db)):
     }
 
 
+@router.get("/geo/satellites")
+async def get_satellites_geojson(
+    limit: Optional[int] = Query(
+        None,
+        ge=1,
+        description="Maximum number of satellites to return. Omit for no limit.",
+    ),
+    db: AsyncSession = Depends(get_db),
+):
+    """获取卫星 TLE GeoJSON 数据"""
+    stmt = (
+        select(CollectedData)
+        .where(CollectedData.source == "celestrak_tle")
+        .where(CollectedData.name != "Unknown")
+        .order_by(CollectedData.id.desc())
+    )
+    if limit is not None:
+        stmt = stmt.limit(limit)
+    result = await db.execute(stmt)
+    records = result.scalars().all()
+
+    if not records:
+        return {"type": "FeatureCollection", "features": [], "count": 0}
+
+    geojson = convert_satellite_to_geojson(list(records))
+    return {
+        **geojson,
+        "count": len(geojson.get("features", [])),
+    }
+
+
+@router.get("/geo/supercomputers")
+async def get_supercomputers_geojson(
+    limit: int = 500,
+    db: AsyncSession = Depends(get_db),
+):
+    """获取 TOP500 超算中心 GeoJSON 数据"""
+    stmt = (
+        select(CollectedData)
+        .where(CollectedData.source == "top500")
+        .where(CollectedData.name != "Unknown")
+        .limit(limit)
+    )
+    result = await db.execute(stmt)
+    records = result.scalars().all()
+
+    if not records:
+        return {"type": "FeatureCollection", "features": [], "count": 0}
+
+    geojson = convert_supercomputer_to_geojson(list(records))
+    return {
+        **geojson,
+        "count": len(geojson.get("features", [])),
+    }
+
+
+@router.get("/geo/gpu-clusters")
+async def get_gpu_clusters_geojson(
+    limit: int = 100,
+    db: AsyncSession = Depends(get_db),
+):
+    """获取 GPU 集群 GeoJSON 数据"""
+    stmt = (
+        select(CollectedData)
+        .where(CollectedData.source == "epoch_ai_gpu")
+        .where(CollectedData.name != "Unknown")
+        .limit(limit)
+    )
+    result = await db.execute(stmt)
+    records = result.scalars().all()
+
+    if not records:
+        return {"type": "FeatureCollection", "features": [], "count": 0}
+
+    geojson = convert_gpu_cluster_to_geojson(list(records))
+    return {
+        **geojson,
+        "count": len(geojson.get("features", [])),
+    }
+
+
+@router.get("/geo/bgp-anomalies")
+async def get_bgp_anomalies_geojson(
+    severity: Optional[str] = Query(None),
+    status: Optional[str] = Query("active"),
+    limit: int = Query(200, ge=1, le=1000),
+    db: AsyncSession = Depends(get_db),
+):
+    stmt = select(BGPAnomaly).order_by(BGPAnomaly.created_at.desc()).limit(limit)
+    if severity:
+        stmt = stmt.where(BGPAnomaly.severity == severity)
+    if status:
+        stmt = stmt.where(BGPAnomaly.status == status)
+
+    result = await db.execute(stmt)
+    records = list(result.scalars().all())
+    geojson = convert_bgp_anomalies_to_geojson(records)
+    return {**geojson, "count": len(geojson.get("features", []))}
+
+
+@router.get("/geo/bgp-collectors")
+async def get_bgp_collectors_geojson():
+    geojson = convert_bgp_collectors_to_geojson()
+    return {**geojson, "count": len(geojson.get("features", []))}
+
+
+@router.get("/all")
+async def get_all_visualization_data(db: AsyncSession = Depends(get_db)):
+    """获取所有可视化数据的统一端点
+
+    Returns GeoJSON FeatureCollections for all data types:
+    - satellites: 卫星 TLE 数据
+    - cables: 海底电缆
+    - landing_points: 登陆点
+    - supercomputers: TOP500 超算
+    - gpu_clusters: GPU 集群
+    """
+    cables_stmt = select(CollectedData).where(CollectedData.source == "arcgis_cables")
+    cables_result = await db.execute(cables_stmt)
+    cables_records = list(cables_result.scalars().all())
+
+    points_stmt = select(CollectedData).where(CollectedData.source == "arcgis_landing_points")
+    points_result = await db.execute(points_stmt)
+    points_records = list(points_result.scalars().all())
+
+    satellites_stmt = (
+        select(CollectedData)
+        .where(CollectedData.source == "celestrak_tle")
+        .where(CollectedData.name != "Unknown")
+    )
+    satellites_result = await db.execute(satellites_stmt)
+    satellites_records = list(satellites_result.scalars().all())
+
+    supercomputers_stmt = (
+        select(CollectedData)
+        .where(CollectedData.source == "top500")
+        .where(CollectedData.name != "Unknown")
+    )
+    supercomputers_result = await db.execute(supercomputers_stmt)
+    supercomputers_records = list(supercomputers_result.scalars().all())
+
+    gpu_stmt = (
+        select(CollectedData)
+        .where(CollectedData.source == "epoch_ai_gpu")
+        .where(CollectedData.name != "Unknown")
+    )
+    gpu_result = await db.execute(gpu_stmt)
+    gpu_records = list(gpu_result.scalars().all())
+
+    cables = (
+        convert_cable_to_geojson(cables_records)
+        if cables_records
+        else {"type": "FeatureCollection", "features": []}
+    )
+    landing_points = (
+        convert_landing_point_to_geojson(points_records)
+        if points_records
+        else {"type": "FeatureCollection", "features": []}
+    )
+    satellites = (
+        convert_satellite_to_geojson(satellites_records)
+        if satellites_records
+        else {"type": "FeatureCollection", "features": []}
+    )
+    supercomputers = (
+        convert_supercomputer_to_geojson(supercomputers_records)
+        if supercomputers_records
+        else {"type": "FeatureCollection", "features": []}
+    )
+    gpu_clusters = (
+        convert_gpu_cluster_to_geojson(gpu_records)
+        if gpu_records
+        else {"type": "FeatureCollection", "features": []}
+    )
+
+    return {
+        "generated_at": to_iso8601_utc(datetime.now(UTC)),
+        "version": "1.0",
+        "data": {
+            "satellites": satellites,
+            "cables": cables,
+            "landing_points": landing_points,
+            "supercomputers": supercomputers,
+            "gpu_clusters": gpu_clusters,
+        },
+        "stats": {
+            "total_features": (
+                len(satellites.get("features", []))
+                + len(cables.get("features", []))
+                + len(landing_points.get("features", []))
+                + len(supercomputers.get("features", []))
+                + len(gpu_clusters.get("features", []))
+            ),
+            "satellites": len(satellites.get("features", [])),
+            "cables": len(cables.get("features", [])),
+            "landing_points": len(landing_points.get("features", [])),
+            "supercomputers": len(supercomputers.get("features", [])),
+            "gpu_clusters": len(gpu_clusters.get("features", [])),
+        },
+    }
+
+
 # Cache for cable graph
 _cable_graph: Optional[CableGraph] = None
 
@@ -208,7 +691,7 @@ async def get_cable_graph(db: AsyncSession) -> CableGraph:
         cables_result = await db.execute(cables_stmt)
         cables_records = list(cables_result.scalars().all())
 
-        points_stmt = select(CollectedData).where(CollectedData.source == "fao_landing_points")
+        points_stmt = select(CollectedData).where(CollectedData.source == "arcgis_landing_points")
         points_result = await db.execute(points_stmt)
         points_records = list(points_result.scalars().all())
 

backend/app/api/v1/websocket.py

@@ -3,13 +3,14 @@
 import asyncio
 import json
 import logging
-from datetime import datetime
+from datetime import UTC, datetime
 from typing import Optional
 
 from fastapi import APIRouter, WebSocket, WebSocketDisconnect, Query
 from jose import jwt, JWTError
 
 from app.core.config import settings
+from app.core.time import to_iso8601_utc
 from app.core.websocket.manager import manager
 
 logger = logging.getLogger(__name__)
@@ -59,6 +60,7 @@ async def websocket_endpoint(
                         "ixp_nodes",
                         "alerts",
                         "dashboard",
+                        "datasource_tasks",
                     ],
                 },
             }
@@ -72,7 +74,7 @@ async def websocket_endpoint(
                     await websocket.send_json(
                         {
                             "type": "heartbeat",
-                            "data": {"action": "pong", "timestamp": datetime.utcnow().isoformat()},
+                            "data": {"action": "pong", "timestamp": to_iso8601_utc(datetime.now(UTC))},
                         }
                     )
                 elif data.get("type") == "subscribe":

backend/app/core/collected_data_fields.py

@@ -0,0 +1,62 @@
+from typing import Any, Dict, Optional
+
+
+FIELD_ALIASES = {
+    "country": ("country",),
+    "city": ("city",),
+    "latitude": ("latitude",),
+    "longitude": ("longitude",),
+    "value": ("value",),
+    "unit": ("unit",),
+    "cores": ("cores",),
+    "rmax": ("rmax", "r_max"),
+    "rpeak": ("rpeak", "r_peak"),
+    "power": ("power",),
+}
+
+
+def get_metadata_field(metadata: Optional[Dict[str, Any]], field: str, fallback: Any = None) -> Any:
+    if isinstance(metadata, dict):
+        for key in FIELD_ALIASES.get(field, (field,)):
+            value = metadata.get(key)
+            if value not in (None, ""):
+                return value
+    return fallback
+
+
+def build_dynamic_metadata(
+    metadata: Optional[Dict[str, Any]],
+    *,
+    country: Any = None,
+    city: Any = None,
+    latitude: Any = None,
+    longitude: Any = None,
+    value: Any = None,
+    unit: Any = None,
+) -> Dict[str, Any]:
+    merged = dict(metadata) if isinstance(metadata, dict) else {}
+
+    fallbacks = {
+        "country": country,
+        "city": city,
+        "latitude": latitude,
+        "longitude": longitude,
+        "value": value,
+        "unit": unit,
+    }
+
+    for field, fallback in fallbacks.items():
+        if fallback not in (None, "") and get_metadata_field(merged, field) in (None, ""):
+            merged[field] = fallback
+
+    return merged
+
+
+def get_record_field(record: Any, field: str) -> Any:
+    metadata = getattr(record, "extra_data", None) or {}
+    fallback_attr = field
+    if field in {"cores", "rmax", "rpeak", "power"}:
+        fallback = None
+    else:
+        fallback = getattr(record, fallback_attr, None)
+    return get_metadata_field(metadata, field, fallback=fallback)

backend/app/core/config.py

@@ -6,9 +6,16 @@ import os
 from pydantic_settings import BaseSettings
 
 
+ROOT_DIR = Path(__file__).parent.parent.parent.parent
+VERSION_FILE = ROOT_DIR / "VERSION"
+
+
 class Settings(BaseSettings):
     PROJECT_NAME: str = "Intelligent Planet Plan"
-    VERSION: str = "1.0.0"
+    VERSION: str = (
+        os.getenv("APP_VERSION")
+        or (VERSION_FILE.read_text(encoding="utf-8").strip() if VERSION_FILE.exists() else "0.19.0")
+    )
     API_V1_STR: str = "/api/v1"
     SECRET_KEY: str = "your-secret-key-change-in-production"
     ALGORITHM: str = "HS256"
@@ -27,6 +34,9 @@ class Settings(BaseSettings):
 
     CORS_ORIGINS: List[str] = ["http://localhost:3000", "http://localhost:8000"]
 
+    SPACETRACK_USERNAME: str = ""
+    SPACETRACK_PASSWORD: str = ""
+
     @property
     def REDIS_URL(self) -> str:
         return os.getenv(
@@ -34,7 +44,7 @@ class Settings(BaseSettings):
         )
 
     class Config:
-        env_file = ".env"
+        env_file = Path(__file__).parent.parent.parent / ".env"
         case_sensitive = True
 
 

backend/app/core/countries.py

@@ -0,0 +1,280 @@
+import re
+from typing import Any, Optional
+
+
+COUNTRY_ENTRIES = [
+    ("阿富汗", ["Afghanistan", "AF", "AFG"]),
+    ("阿尔巴尼亚", ["Albania", "AL", "ALB"]),
+    ("阿尔及利亚", ["Algeria", "DZ", "DZA"]),
+    ("安道尔", ["Andorra", "AD", "AND"]),
+    ("安哥拉", ["Angola", "AO", "AGO"]),
+    ("安提瓜和巴布达", ["Antigua and Barbuda", "AG", "ATG"]),
+    ("阿根廷", ["Argentina", "AR", "ARG"]),
+    ("亚美尼亚", ["Armenia", "AM", "ARM"]),
+    ("澳大利亚", ["Australia", "AU", "AUS"]),
+    ("奥地利", ["Austria", "AT", "AUT"]),
+    ("阿塞拜疆", ["Azerbaijan", "AZ", "AZE"]),
+    ("巴哈马", ["Bahamas", "BS", "BHS"]),
+    ("巴林", ["Bahrain", "BH", "BHR"]),
+    ("孟加拉国", ["Bangladesh", "BD", "BGD"]),
+    ("巴巴多斯", ["Barbados", "BB", "BRB"]),
+    ("白俄罗斯", ["Belarus", "BY", "BLR"]),
+    ("比利时", ["Belgium", "BE", "BEL"]),
+    ("伯利兹", ["Belize", "BZ", "BLZ"]),
+    ("贝宁", ["Benin", "BJ", "BEN"]),
+    ("不丹", ["Bhutan", "BT", "BTN"]),
+    ("玻利维亚", ["Bolivia", "BO", "BOL", "Bolivia (Plurinational State of)"]),
+    ("波斯尼亚和黑塞哥维那", ["Bosnia and Herzegovina", "BA", "BIH"]),
+    ("博茨瓦纳", ["Botswana", "BW", "BWA"]),
+    ("巴西", ["Brazil", "BR", "BRA"]),
+    ("文莱", ["Brunei", "BN", "BRN", "Brunei Darussalam"]),
+    ("保加利亚", ["Bulgaria", "BG", "BGR"]),
+    ("布基纳法索", ["Burkina Faso", "BF", "BFA"]),
+    ("布隆迪", ["Burundi", "BI", "BDI"]),
+    ("柬埔寨", ["Cambodia", "KH", "KHM"]),
+    ("喀麦隆", ["Cameroon", "CM", "CMR"]),
+    ("加拿大", ["Canada", "CA", "CAN"]),
+    ("佛得角", ["Cape Verde", "CV", "CPV", "Cabo Verde"]),
+    ("中非", ["Central African Republic", "CF", "CAF"]),
+    ("乍得", ["Chad", "TD", "TCD"]),
+    ("智利", ["Chile", "CL", "CHL"]),
+    ("中国", ["China", "CN", "CHN", "Mainland China", "PRC", "People's Republic of China"]),
+    ("中国（香港）", ["Hong Kong", "HK", "HKG", "Hong Kong SAR", "China Hong Kong", "Hong Kong, China"]),
+    ("中国（澳门）", ["Macao", "Macau", "MO", "MAC", "Macao SAR", "China Macao", "Macau, China"]),
+    ("中国（台湾）", ["Taiwan", "TW", "TWN", "Chinese Taipei", "Taiwan, China"]),
+    ("哥伦比亚", ["Colombia", "CO", "COL"]),
+    ("科摩罗", ["Comoros", "KM", "COM"]),
+    ("刚果（布）", ["Republic of the Congo", "Congo", "Congo-Brazzaville", "CG", "COG"]),
+    ("刚果（金）", ["Democratic Republic of the Congo", "DR Congo", "Congo-Kinshasa", "CD", "COD"]),
+    ("哥斯达黎加", ["Costa Rica", "CR", "CRI"]),
+    ("科特迪瓦", ["Cote d'Ivoire", "Côte d'Ivoire", "Ivory Coast", "CI", "CIV"]),
+    ("克罗地亚", ["Croatia", "HR", "HRV"]),
+    ("古巴", ["Cuba", "CU", "CUB"]),
+    ("塞浦路斯", ["Cyprus", "CY", "CYP"]),
+    ("捷克", ["Czech Republic", "Czechia", "CZ", "CZE"]),
+    ("丹麦", ["Denmark", "DK", "DNK"]),
+    ("吉布提", ["Djibouti", "DJ", "DJI"]),
+    ("多米尼克", ["Dominica", "DM", "DMA"]),
+    ("多米尼加", ["Dominican Republic", "DO", "DOM"]),
+    ("厄瓜多尔", ["Ecuador", "EC", "ECU"]),
+    ("埃及", ["Egypt", "EG", "EGY"]),
+    ("萨尔瓦多", ["El Salvador", "SV", "SLV"]),
+    ("赤道几内亚", ["Equatorial Guinea", "GQ", "GNQ"]),
+    ("厄立特里亚", ["Eritrea", "ER", "ERI"]),
+    ("爱沙尼亚", ["Estonia", "EE", "EST"]),
+    ("埃斯瓦蒂尼", ["Eswatini", "SZ", "SWZ", "Swaziland"]),
+    ("埃塞俄比亚", ["Ethiopia", "ET", "ETH"]),
+    ("斐济", ["Fiji", "FJ", "FJI"]),
+    ("芬兰", ["Finland", "FI", "FIN"]),
+    ("法国", ["France", "FR", "FRA"]),
+    ("加蓬", ["Gabon", "GA", "GAB"]),
+    ("冈比亚", ["Gambia", "GM", "GMB"]),
+    ("格鲁吉亚", ["Georgia", "GE", "GEO"]),
+    ("德国", ["Germany", "DE", "DEU"]),
+    ("加纳", ["Ghana", "GH", "GHA"]),
+    ("希腊", ["Greece", "GR", "GRC"]),
+    ("格林纳达", ["Grenada", "GD", "GRD"]),
+    ("危地马拉", ["Guatemala", "GT", "GTM"]),
+    ("几内亚", ["Guinea", "GN", "GIN"]),
+    ("几内亚比绍", ["Guinea-Bissau", "GW", "GNB"]),
+    ("圭亚那", ["Guyana", "GY", "GUY"]),
+    ("海地", ["Haiti", "HT", "HTI"]),
+    ("洪都拉斯", ["Honduras", "HN", "HND"]),
+    ("匈牙利", ["Hungary", "HU", "HUN"]),
+    ("冰岛", ["Iceland", "IS", "ISL"]),
+    ("印度", ["India", "IN", "IND"]),
+    ("印度尼西亚", ["Indonesia", "ID", "IDN"]),
+    ("伊朗", ["Iran", "IR", "IRN", "Iran (Islamic Republic of)"]),
+    ("伊拉克", ["Iraq", "IQ", "IRQ"]),
+    ("爱尔兰", ["Ireland", "IE", "IRL"]),
+    ("以色列", ["Israel", "IL", "ISR"]),
+    ("意大利", ["Italy", "IT", "ITA"]),
+    ("牙买加", ["Jamaica", "JM", "JAM"]),
+    ("日本", ["Japan", "JP", "JPN"]),
+    ("约旦", ["Jordan", "JO", "JOR"]),
+    ("哈萨克斯坦", ["Kazakhstan", "KZ", "KAZ"]),
+    ("肯尼亚", ["Kenya", "KE", "KEN"]),
+    ("基里巴斯", ["Kiribati", "KI", "KIR"]),
+    ("朝鲜", ["North Korea", "Korea, DPRK", "Democratic People's Republic of Korea", "KP", "PRK"]),
+    ("韩国", ["South Korea", "Republic of Korea", "Korea", "KR", "KOR"]),
+    ("科威特", ["Kuwait", "KW", "KWT"]),
+    ("吉尔吉斯斯坦", ["Kyrgyzstan", "KG", "KGZ"]),
+    ("老挝", ["Laos", "Lao PDR", "Lao People's Democratic Republic", "LA", "LAO"]),
+    ("拉脱维亚", ["Latvia", "LV", "LVA"]),
+    ("黎巴嫩", ["Lebanon", "LB", "LBN"]),
+    ("莱索托", ["Lesotho", "LS", "LSO"]),
+    ("利比里亚", ["Liberia", "LR", "LBR"]),
+    ("利比亚", ["Libya", "LY", "LBY"]),
+    ("列支敦士登", ["Liechtenstein", "LI", "LIE"]),
+    ("立陶宛", ["Lithuania", "LT", "LTU"]),
+    ("卢森堡", ["Luxembourg", "LU", "LUX"]),
+    ("马达加斯加", ["Madagascar", "MG", "MDG"]),
+    ("马拉维", ["Malawi", "MW", "MWI"]),
+    ("马来西亚", ["Malaysia", "MY", "MYS"]),
+    ("马尔代夫", ["Maldives", "MV", "MDV"]),
+    ("马里", ["Mali", "ML", "MLI"]),
+    ("马耳他", ["Malta", "MT", "MLT"]),
+    ("马绍尔群岛", ["Marshall Islands", "MH", "MHL"]),
+    ("毛里塔尼亚", ["Mauritania", "MR", "MRT"]),
+    ("毛里求斯", ["Mauritius", "MU", "MUS"]),
+    ("墨西哥", ["Mexico", "MX", "MEX"]),
+    ("密克罗尼西亚", ["Micronesia", "FM", "FSM", "Federated States of Micronesia"]),
+    ("摩尔多瓦", ["Moldova", "MD", "MDA", "Republic of Moldova"]),
+    ("摩纳哥", ["Monaco", "MC", "MCO"]),
+    ("蒙古", ["Mongolia", "MN", "MNG"]),
+    ("黑山", ["Montenegro", "ME", "MNE"]),
+    ("摩洛哥", ["Morocco", "MA", "MAR"]),
+    ("莫桑比克", ["Mozambique", "MZ", "MOZ"]),
+    ("缅甸", ["Myanmar", "MM", "MMR", "Burma"]),
+    ("纳米比亚", ["Namibia", "NA", "NAM"]),
+    ("瑙鲁", ["Nauru", "NR", "NRU"]),
+    ("尼泊尔", ["Nepal", "NP", "NPL"]),
+    ("荷兰", ["Netherlands", "NL", "NLD"]),
+    ("新西兰", ["New Zealand", "NZ", "NZL"]),
+    ("尼加拉瓜", ["Nicaragua", "NI", "NIC"]),
+    ("尼日尔", ["Niger", "NE", "NER"]),
+    ("尼日利亚", ["Nigeria", "NG", "NGA"]),
+    ("北马其顿", ["North Macedonia", "MK", "MKD", "Macedonia"]),
+    ("挪威", ["Norway", "NO", "NOR"]),
+    ("阿曼", ["Oman", "OM", "OMN"]),
+    ("巴基斯坦", ["Pakistan", "PK", "PAK"]),
+    ("帕劳", ["Palau", "PW", "PLW"]),
+    ("巴勒斯坦", ["Palestine", "PS", "PSE", "State of Palestine"]),
+    ("巴拿马", ["Panama", "PA", "PAN"]),
+    ("巴布亚新几内亚", ["Papua New Guinea", "PG", "PNG"]),
+    ("巴拉圭", ["Paraguay", "PY", "PRY"]),
+    ("秘鲁", ["Peru", "PE", "PER"]),
+    ("菲律宾", ["Philippines", "PH", "PHL"]),
+    ("波兰", ["Poland", "PL", "POL"]),
+    ("葡萄牙", ["Portugal", "PT", "PRT"]),
+    ("卡塔尔", ["Qatar", "QA", "QAT"]),
+    ("罗马尼亚", ["Romania", "RO", "ROU"]),
+    ("俄罗斯", ["Russia", "Russian Federation", "RU", "RUS"]),
+    ("卢旺达", ["Rwanda", "RW", "RWA"]),
+    ("圣基茨和尼维斯", ["Saint Kitts and Nevis", "KN", "KNA"]),
+    ("圣卢西亚", ["Saint Lucia", "LC", "LCA"]),
+    ("圣文森特和格林纳丁斯", ["Saint Vincent and the Grenadines", "VC", "VCT"]),
+    ("萨摩亚", ["Samoa", "WS", "WSM"]),
+    ("圣马力诺", ["San Marino", "SM", "SMR"]),
+    ("圣多美和普林西比", ["Sao Tome and Principe", "ST", "STP", "São Tomé and Príncipe"]),
+    ("沙特阿拉伯", ["Saudi Arabia", "SA", "SAU"]),
+    ("塞内加尔", ["Senegal", "SN", "SEN"]),
+    ("塞尔维亚", ["Serbia", "RS", "SRB", "Kosovo", "XK", "XKS", "Republic of Kosovo"]),
+    ("塞舌尔", ["Seychelles", "SC", "SYC"]),
+    ("塞拉利昂", ["Sierra Leone", "SL", "SLE"]),
+    ("新加坡", ["Singapore", "SG", "SGP"]),
+    ("斯洛伐克", ["Slovakia", "SK", "SVK"]),
+    ("斯洛文尼亚", ["Slovenia", "SI", "SVN"]),
+    ("所罗门群岛", ["Solomon Islands", "SB", "SLB"]),
+    ("索马里", ["Somalia", "SO", "SOM"]),
+    ("南非", ["South Africa", "ZA", "ZAF"]),
+    ("南苏丹", ["South Sudan", "SS", "SSD"]),
+    ("西班牙", ["Spain", "ES", "ESP"]),
+    ("斯里兰卡", ["Sri Lanka", "LK", "LKA"]),
+    ("苏丹", ["Sudan", "SD", "SDN"]),
+    ("苏里南", ["Suriname", "SR", "SUR"]),
+    ("瑞典", ["Sweden", "SE", "SWE"]),
+    ("瑞士", ["Switzerland", "CH", "CHE"]),
+    ("叙利亚", ["Syria", "SY", "SYR", "Syrian Arab Republic"]),
+    ("塔吉克斯坦", ["Tajikistan", "TJ", "TJK"]),
+    ("坦桑尼亚", ["Tanzania", "TZ", "TZA", "United Republic of Tanzania"]),
+    ("泰国", ["Thailand", "TH", "THA"]),
+    ("东帝汶", ["Timor-Leste", "East Timor", "TL", "TLS"]),
+    ("多哥", ["Togo", "TG", "TGO"]),
+    ("汤加", ["Tonga", "TO", "TON"]),
+    ("特立尼达和多巴哥", ["Trinidad and Tobago", "TT", "TTO"]),
+    ("突尼斯", ["Tunisia", "TN", "TUN"]),
+    ("土耳其", ["Turkey", "TR", "TUR", "Türkiye"]),
+    ("土库曼斯坦", ["Turkmenistan", "TM", "TKM"]),
+    ("图瓦卢", ["Tuvalu", "TV", "TUV"]),
+    ("乌干达", ["Uganda", "UG", "UGA"]),
+    ("乌克兰", ["Ukraine", "UA", "UKR"]),
+    ("阿联酋", ["United Arab Emirates", "AE", "ARE", "UAE"]),
+    ("英国", ["United Kingdom", "UK", "GB", "GBR", "Great Britain", "Britain", "England"]),
+    ("美国", ["United States", "United States of America", "US", "USA", "U.S.", "U.S.A."]),
+    ("乌拉圭", ["Uruguay", "UY", "URY"]),
+    ("乌兹别克斯坦", ["Uzbekistan", "UZ", "UZB"]),
+    ("瓦努阿图", ["Vanuatu", "VU", "VUT"]),
+    ("梵蒂冈", ["Vatican City", "Holy See", "VA", "VAT"]),
+    ("委内瑞拉", ["Venezuela", "VE", "VEN", "Venezuela (Bolivarian Republic of)"]),
+    ("越南", ["Vietnam", "Viet Nam", "VN", "VNM"]),
+    ("也门", ["Yemen", "YE", "YEM"]),
+    ("赞比亚", ["Zambia", "ZM", "ZMB"]),
+    ("津巴布韦", ["Zimbabwe", "ZW", "ZWE"]),
+]
+
+
+COUNTRY_OPTIONS = [entry[0] for entry in COUNTRY_ENTRIES]
+CANONICAL_COUNTRY_SET = set(COUNTRY_OPTIONS)
+INVALID_COUNTRY_VALUES = {
+    "",
+    "-",
+    "--",
+    "unknown",
+    "n/a",
+    "na",
+    "none",
+    "null",
+    "global",
+    "world",
+    "worldwide",
+    "xx",
+}
+NUMERIC_LIKE_PATTERN = re.compile(r"^[\d\s,._%+\-]+$")
+
+COUNTRY_ALIAS_MAP = {}
+COUNTRY_VARIANTS_MAP = {}
+for canonical, aliases in COUNTRY_ENTRIES:
+    COUNTRY_ALIAS_MAP[canonical.casefold()] = canonical
+    variants = [canonical, *aliases]
+    COUNTRY_VARIANTS_MAP[canonical] = variants
+    for alias in aliases:
+        COUNTRY_ALIAS_MAP[alias.casefold()] = canonical
+
+
+def normalize_country(value: Any) -> Optional[str]:
+    if value is None:
+        return None
+
+    if not isinstance(value, str):
+        return None
+
+    normalized = re.sub(r"\s+", " ", value.strip())
+    normalized = normalized.replace("(", "（").replace(")", "）")
+
+    if not normalized:
+        return None
+
+    lowered = normalized.casefold()
+    if lowered in INVALID_COUNTRY_VALUES:
+        return None
+
+    if NUMERIC_LIKE_PATTERN.fullmatch(normalized):
+        return None
+
+    if normalized in CANONICAL_COUNTRY_SET:
+        return normalized
+
+    return COUNTRY_ALIAS_MAP.get(lowered)
+
+
+def get_country_search_variants(value: Any) -> list[str]:
+    canonical = normalize_country(value)
+    if canonical is None:
+        return []
+
+    variants = []
+    seen = set()
+    for item in COUNTRY_VARIANTS_MAP.get(canonical, [canonical]):
+        if not isinstance(item, str):
+            continue
+        normalized = re.sub(r"\s+", " ", item.strip())
+        if not normalized:
+            continue
+        key = normalized.casefold()
+        if key in seen:
+            continue
+        seen.add(key)
+        variants.append(normalized)
+
+    return variants

backend/app/core/data_sources.py

@@ -0,0 +1,81 @@
+import os
+import yaml
+from functools import lru_cache
+from typing import Optional
+
+
+COLLECTOR_URL_KEYS = {
+    "arcgis_cables": "arcgis.cable_url",
+    "arcgis_landing_points": "arcgis.landing_point_url",
+    "arcgis_cable_landing_relation": "arcgis.cable_landing_relation_url",
+    "fao_landing_points": "fao.landing_point_url",
+    "telegeography_cables": "telegeography.cable_url",
+    "telegeography_landing": "telegeography.landing_point_url",
+    "huggingface_models": "huggingface.models_url",
+    "huggingface_datasets": "huggingface.datasets_url",
+    "huggingface_spaces": "huggingface.spaces_url",
+    "cloudflare_radar_device": "cloudflare.radar_device_url",
+    "cloudflare_radar_traffic": "cloudflare.radar_traffic_url",
+    "cloudflare_radar_top_locations": "cloudflare.radar_top_locations_url",
+    "peeringdb_ixp": "peeringdb.ixp_url",
+    "peeringdb_network": "peeringdb.network_url",
+    "peeringdb_facility": "peeringdb.facility_url",
+    "top500": "top500.url",
+    "epoch_ai_gpu": "epoch_ai.gpu_clusters_url",
+    "spacetrack_tle": "spacetrack.tle_query_url",
+    "ris_live_bgp": "ris_live.url",
+    "bgpstream_bgp": "bgpstream.url",
+}
+
+
+class DataSourcesConfig:
+    def __init__(self, config_path: str = None):
+        if config_path is None:
+            config_path = os.path.join(os.path.dirname(__file__), "data_sources.yaml")
+
+        self._yaml_config = {}
+        if os.path.exists(config_path):
+            with open(config_path, "r") as f:
+                self._yaml_config = yaml.safe_load(f) or {}
+
+    def get_yaml_url(self, collector_name: str) -> str:
+        key = COLLECTOR_URL_KEYS.get(collector_name, "")
+        if not key:
+            return ""
+
+        parts = key.split(".")
+        value = self._yaml_config
+        for part in parts:
+            if isinstance(value, dict):
+                value = value.get(part, "")
+            else:
+                return ""
+        return value if isinstance(value, str) else ""
+
+    async def get_url(self, collector_name: str, db) -> str:
+        yaml_url = self.get_yaml_url(collector_name)
+
+        if not db:
+            return yaml_url
+
+        try:
+            from sqlalchemy import select
+            from app.models.datasource_config import DataSourceConfig
+
+            query = select(DataSourceConfig).where(
+                DataSourceConfig.name == collector_name, DataSourceConfig.is_active == True
+            )
+            result = await db.execute(query)
+            db_config = result.scalar_one_or_none()
+
+            if db_config and db_config.endpoint:
+                return db_config.endpoint
+        except Exception:
+            pass
+
+        return yaml_url
+
+
+@lru_cache()
+def get_data_sources_config() -> DataSourcesConfig:
+    return DataSourcesConfig()

backend/app/core/data_sources.yaml

@@ -0,0 +1,45 @@
+# Data Sources Configuration
+# All external data source URLs should be configured here
+
+arcgis:
+  cable_url: "https://services.arcgis.com/6DIQcwlPy8knb6sg/ArcGIS/rest/services/SubmarineCables/FeatureServer/2/query"
+  landing_point_url: "https://services.arcgis.com/6DIQcwlPy8knb6sg/ArcGIS/rest/services/SubmarineCables/FeatureServer/1/query"
+  cable_landing_relation_url: "https://services.arcgis.com/6DIQcwlPy8knb6sg/ArcGIS/rest/services/SubmarineCables/FeatureServer/3/query"
+
+fao:
+  landing_point_url: "https://data.apps.fao.org/catalog/dataset/1b75ff21-92f2-4b96-9b7b-98e8aa65ad5d/resource/b6071077-d1d4-4e97-aa00-42e902847c87/download/landing-point-geo.csv"
+
+telegeography:
+  cable_url: "https://raw.githubusercontent.com/lintaojlu/submarine_cable_information/main/cable.json"
+  landing_point_url: "https://raw.githubusercontent.com/lintaojlu/submarine_cable_information/main/landing_point.json"
+
+huggingface:
+  models_url: "https://huggingface.co/api/models"
+  datasets_url: "https://huggingface.co/api/datasets"
+  spaces_url: "https://huggingface.co/api/spaces"
+
+cloudflare:
+  radar_device_url: "https://api.cloudflare.com/client/v4/radar/http/summary/device_type"
+  radar_traffic_url: "https://api.cloudflare.com/client/v4/radar/http/timeseries/requests"
+  radar_top_locations_url: "https://api.cloudflare.com/client/v4/radar/http/top/locations"
+
+peeringdb:
+  ixp_url: "https://www.peeringdb.com/api/ix"
+  network_url: "https://www.peeringdb.com/api/net"
+  facility_url: "https://www.peeringdb.com/api/fac"
+
+top500:
+  url: "https://top500.org/lists/top500/list/2025/11/"
+
+epoch_ai:
+  gpu_clusters_url: "https://epoch.ai/data/gpu-clusters"
+
+spacetrack:
+  base_url: "https://www.space-track.org"
+  tle_query_url: "https://www.space-track.org/basicspacedata/query/class/gp/orderby/EPOCH%20desc/limit/1000/format/json"
+
+ris_live:
+  url: "https://ris-live.ripe.net/v1/stream/?format=json&client=planet-ris-live"
+
+bgpstream:
+  url: "https://broker.bgpstream.caida.org/v2"

backend/app/core/datasource_defaults.py

@@ -0,0 +1,140 @@
+"""Default built-in datasource definitions."""
+
+DEFAULT_DATASOURCES = {
+    "top500": {
+        "id": 1,
+        "name": "TOP500 Supercomputers",
+        "module": "L1",
+        "priority": "P0",
+        "frequency_minutes": 240,
+    },
+    "epoch_ai_gpu": {
+        "id": 2,
+        "name": "Epoch AI GPU Clusters",
+        "module": "L1",
+        "priority": "P0",
+        "frequency_minutes": 360,
+    },
+    "huggingface_models": {
+        "id": 3,
+        "name": "HuggingFace Models",
+        "module": "L2",
+        "priority": "P1",
+        "frequency_minutes": 720,
+    },
+    "huggingface_datasets": {
+        "id": 4,
+        "name": "HuggingFace Datasets",
+        "module": "L2",
+        "priority": "P1",
+        "frequency_minutes": 720,
+    },
+    "huggingface_spaces": {
+        "id": 5,
+        "name": "HuggingFace Spaces",
+        "module": "L2",
+        "priority": "P2",
+        "frequency_minutes": 1440,
+    },
+    "peeringdb_ixp": {
+        "id": 6,
+        "name": "PeeringDB IXP",
+        "module": "L2",
+        "priority": "P1",
+        "frequency_minutes": 1440,
+    },
+    "peeringdb_network": {
+        "id": 7,
+        "name": "PeeringDB Networks",
+        "module": "L2",
+        "priority": "P2",
+        "frequency_minutes": 2880,
+    },
+    "peeringdb_facility": {
+        "id": 8,
+        "name": "PeeringDB Facilities",
+        "module": "L2",
+        "priority": "P2",
+        "frequency_minutes": 2880,
+    },
+    "telegeography_cables": {
+        "id": 9,
+        "name": "Submarine Cables",
+        "module": "L2",
+        "priority": "P1",
+        "frequency_minutes": 10080,
+    },
+    "telegeography_landing": {
+        "id": 10,
+        "name": "Cable Landing Points",
+        "module": "L2",
+        "priority": "P2",
+        "frequency_minutes": 10080,
+    },
+    "telegeography_systems": {
+        "id": 11,
+        "name": "Cable Systems",
+        "module": "L2",
+        "priority": "P2",
+        "frequency_minutes": 10080,
+    },
+    "arcgis_cables": {
+        "id": 15,
+        "name": "ArcGIS Submarine Cables",
+        "module": "L2",
+        "priority": "P1",
+        "frequency_minutes": 10080,
+    },
+    "arcgis_landing_points": {
+        "id": 16,
+        "name": "ArcGIS Landing Points",
+        "module": "L2",
+        "priority": "P1",
+        "frequency_minutes": 10080,
+    },
+    "arcgis_cable_landing_relation": {
+        "id": 17,
+        "name": "ArcGIS Cable-Landing Relations",
+        "module": "L2",
+        "priority": "P1",
+        "frequency_minutes": 10080,
+    },
+    "fao_landing_points": {
+        "id": 18,
+        "name": "FAO Landing Points",
+        "module": "L2",
+        "priority": "P1",
+        "frequency_minutes": 10080,
+    },
+    "spacetrack_tle": {
+        "id": 19,
+        "name": "Space-Track TLE",
+        "module": "L3",
+        "priority": "P2",
+        "frequency_minutes": 1440,
+    },
+    "celestrak_tle": {
+        "id": 20,
+        "name": "CelesTrak TLE",
+        "module": "L3",
+        "priority": "P2",
+        "frequency_minutes": 1440,
+    },
+    "ris_live_bgp": {
+        "id": 21,
+        "name": "RIPE RIS Live BGP",
+        "module": "L3",
+        "priority": "P1",
+        "frequency_minutes": 15,
+    },
+    "bgpstream_bgp": {
+        "id": 22,
+        "name": "CAIDA BGPStream Backfill",
+        "module": "L3",
+        "priority": "P1",
+        "frequency_minutes": 360,
+    },
+}
+
+ID_TO_COLLECTOR = {info["id"]: name for name, info in DEFAULT_DATASOURCES.items()}
+COLLECTOR_TO_ID = {name: info["id"] for name, info in DEFAULT_DATASOURCES.items()}

backend/app/core/satellite_tle.py

@@ -0,0 +1,116 @@
+"""Helpers for building stable TLE lines from orbital elements."""
+
+from __future__ import annotations
+
+from datetime import datetime
+from typing import Any, Optional
+
+
+def compute_tle_checksum(line: str) -> str:
+    """Compute the standard modulo-10 checksum for a TLE line."""
+    total = 0
+
+    for char in line[:68]:
+        if char.isdigit():
+            total += int(char)
+        elif char == "-":
+            total += 1
+
+    return str(total % 10)
+
+
+def _parse_epoch(value: Any) -> Optional[datetime]:
+    if not value:
+        return None
+    if isinstance(value, datetime):
+        return value
+    if isinstance(value, str):
+        return datetime.fromisoformat(value.replace("Z", "+00:00"))
+    return None
+
+
+def build_tle_line1(norad_cat_id: Any, epoch: Any) -> Optional[str]:
+    """Build a valid TLE line 1 from the NORAD id and epoch."""
+    epoch_date = _parse_epoch(epoch)
+    if not norad_cat_id or epoch_date is None:
+        return None
+
+    epoch_year = epoch_date.year % 100
+    start_of_year = datetime(epoch_date.year, 1, 1, tzinfo=epoch_date.tzinfo)
+    day_of_year = (epoch_date - start_of_year).days + 1
+    ms_of_day = (
+        epoch_date.hour * 3600000
+        + epoch_date.minute * 60000
+        + epoch_date.second * 1000
+        + int(epoch_date.microsecond / 1000)
+    )
+    day_fraction = ms_of_day / 86400000
+    decimal_fraction = f"{day_fraction:.8f}"[1:]
+    epoch_str = f"{epoch_year:02d}{day_of_year:03d}{decimal_fraction}"
+
+    core = (
+        f"1 {int(norad_cat_id):05d}U 00001A   {epoch_str}"
+        "  .00000000  00000-0  00000-0 0  999"
+    )
+    return core + compute_tle_checksum(core)
+
+
+def build_tle_line2(
+    norad_cat_id: Any,
+    inclination: Any,
+    raan: Any,
+    eccentricity: Any,
+    arg_of_perigee: Any,
+    mean_anomaly: Any,
+    mean_motion: Any,
+) -> Optional[str]:
+    """Build a valid TLE line 2 from the standard orbital elements."""
+    required = [
+        norad_cat_id,
+        inclination,
+        raan,
+        eccentricity,
+        arg_of_perigee,
+        mean_anomaly,
+        mean_motion,
+    ]
+    if any(value is None for value in required):
+        return None
+
+    eccentricity_digits = str(round(float(eccentricity) * 10_000_000)).zfill(7)
+    core = (
+        f"2 {int(norad_cat_id):05d}"
+        f" {float(inclination):8.4f}"
+        f" {float(raan):8.4f}"
+        f" {eccentricity_digits}"
+        f" {float(arg_of_perigee):8.4f}"
+        f" {float(mean_anomaly):8.4f}"
+        f" {float(mean_motion):11.8f}"
+        "00000"
+    )
+    return core + compute_tle_checksum(core)
+
+
+def build_tle_lines_from_elements(
+    *,
+    norad_cat_id: Any,
+    epoch: Any,
+    inclination: Any,
+    raan: Any,
+    eccentricity: Any,
+    arg_of_perigee: Any,
+    mean_anomaly: Any,
+    mean_motion: Any,
+) -> tuple[Optional[str], Optional[str]]:
+    """Build both TLE lines from a metadata payload."""
+    line1 = build_tle_line1(norad_cat_id, epoch)
+    line2 = build_tle_line2(
+        norad_cat_id,
+        inclination,
+        raan,
+        eccentricity,
+        arg_of_perigee,
+        mean_anomaly,
+        mean_motion,
+    )
+    return line1, line2

backend/app/core/security.py

@@ -1,4 +1,4 @@
-from datetime import datetime, timedelta
+from datetime import UTC, datetime, timedelta
 from typing import Optional
 
 import bcrypt
@@ -49,9 +49,9 @@ def get_password_hash(password: str) -> str:
 def create_access_token(data: dict, expires_delta: Optional[timedelta] = None) -> str:
     to_encode = data.copy()
     if expires_delta:
-        expire = datetime.utcnow() + expires_delta
+        expire = datetime.now(UTC) + expires_delta
     elif settings.ACCESS_TOKEN_EXPIRE_MINUTES > 0:
-        expire = datetime.utcnow() + timedelta(minutes=settings.ACCESS_TOKEN_EXPIRE_MINUTES)
+        expire = datetime.now(UTC) + timedelta(minutes=settings.ACCESS_TOKEN_EXPIRE_MINUTES)
     else:
         expire = None
     if expire:
@@ -65,7 +65,7 @@ def create_access_token(data: dict, expires_delta: Optional[timedelta] = None) -
 def create_refresh_token(data: dict) -> str:
     to_encode = data.copy()
     if settings.REFRESH_TOKEN_EXPIRE_DAYS > 0:
-        expire = datetime.utcnow() + timedelta(days=settings.REFRESH_TOKEN_EXPIRE_DAYS)
+        expire = datetime.now(UTC) + timedelta(days=settings.REFRESH_TOKEN_EXPIRE_DAYS)
         to_encode.update({"exp": expire})
     to_encode.update({"type": "refresh"})
     if "sub" in to_encode:

backend/app/core/time.py

@@ -0,0 +1,20 @@
+"""Time helpers for API serialization."""
+
+from __future__ import annotations
+
+from datetime import UTC, datetime
+
+
+def ensure_utc(value: datetime | None) -> datetime | None:
+    if value is None:
+        return None
+    if value.tzinfo is None:
+        return value.replace(tzinfo=UTC)
+    return value.astimezone(UTC)
+
+
+def to_iso8601_utc(value: datetime | None) -> str | None:
+    normalized = ensure_utc(value)
+    if normalized is None:
+        return None
+    return normalized.isoformat().replace("+00:00", "Z")

backend/app/core/websocket/broadcaster.py

@@ -1,12 +1,14 @@
 """Data broadcaster for WebSocket connections"""
 
 import asyncio
-from datetime import datetime
+from datetime import UTC, datetime
 from typing import Dict, Any, Optional
 
+from app.core.time import to_iso8601_utc
 from app.core.websocket.manager import manager
 
 
+
 class DataBroadcaster:
     """Periodically broadcasts data to connected WebSocket clients"""
 
@@ -21,7 +23,7 @@ class DataBroadcaster:
             "active_datasources": 8,
             "tasks_today": 45,
             "success_rate": 97.8,
-            "last_updated": datetime.utcnow().isoformat(),
+            "last_updated": to_iso8601_utc(datetime.now(UTC)),
             "alerts": {"critical": 0, "warning": 2, "info": 5},
         }
 
@@ -34,7 +36,7 @@ class DataBroadcaster:
                     {
                         "type": "data_frame",
                         "channel": "dashboard",
-                        "timestamp": datetime.utcnow().isoformat(),
+                        "timestamp": to_iso8601_utc(datetime.now(UTC)),
                         "payload": {"stats": stats},
                     },
                     channel="dashboard",
@@ -48,7 +50,7 @@ class DataBroadcaster:
         await manager.broadcast(
             {
                 "type": "alert_notification",
-                "timestamp": datetime.utcnow().isoformat(),
+                "timestamp": to_iso8601_utc(datetime.now(UTC)),
                 "data": {"alert": alert},
             }
         )
@@ -59,7 +61,7 @@ class DataBroadcaster:
             {
                 "type": "data_frame",
                 "channel": "gpu_clusters",
-                "timestamp": datetime.utcnow().isoformat(),
+                "timestamp": to_iso8601_utc(datetime.now(UTC)),
                 "payload": data,
             }
         )
@@ -70,12 +72,24 @@ class DataBroadcaster:
             {
                 "type": "data_frame",
                 "channel": channel,
-                "timestamp": datetime.utcnow().isoformat(),
+                "timestamp": to_iso8601_utc(datetime.now(UTC)),
                 "payload": data,
             },
             channel=channel if channel in manager.active_connections else "all",
         )
 
+    async def broadcast_datasource_task_update(self, data: Dict[str, Any]):
+        """Broadcast datasource task progress updates to connected clients."""
+        await manager.broadcast(
+            {
+                "type": "data_frame",
+                "channel": "datasource_tasks",
+                "timestamp": to_iso8601_utc(datetime.now(UTC)),
+                "payload": data,
+            },
+            channel="all",
+        )
+
     def start(self):
         """Start all broadcasters"""
         if not self.running:

backend/app/db/session.py

@@ -1,5 +1,6 @@
 from typing import AsyncGenerator
 
+from sqlalchemy import text
 from sqlalchemy.ext.asyncio import AsyncSession, create_async_engine, async_sessionmaker
 from sqlalchemy.orm import declarative_base
 
@@ -25,11 +26,126 @@ async def get_db() -> AsyncGenerator[AsyncSession, None]:
             raise
 
 
+async def seed_default_datasources(session: AsyncSession):
+    from app.core.datasource_defaults import DEFAULT_DATASOURCES
+    from app.models.datasource import DataSource
+
+    for source, info in DEFAULT_DATASOURCES.items():
+        existing = await session.get(DataSource, info["id"])
+        if existing:
+            existing.name = info["name"]
+            existing.source = source
+            existing.module = info["module"]
+            existing.priority = info["priority"]
+            existing.frequency_minutes = info["frequency_minutes"]
+            existing.collector_class = source
+            if existing.config is None:
+                existing.config = "{}"
+            continue
+
+        session.add(
+            DataSource(
+                id=info["id"],
+                name=info["name"],
+                source=source,
+                module=info["module"],
+                priority=info["priority"],
+                frequency_minutes=info["frequency_minutes"],
+                collector_class=source,
+                config="{}",
+                is_active=True,
+            )
+        )
+
+    await session.commit()
+
+
+async def ensure_default_admin_user(session: AsyncSession):
+    from app.core.security import get_password_hash
+    from app.models.user import User
+
+    result = await session.execute(
+        text("SELECT id FROM users WHERE username = 'admin'")
+    )
+    if result.fetchone():
+        return
+
+    session.add(
+        User(
+            username="admin",
+            email="admin@planet.local",
+            password_hash=get_password_hash("admin123"),
+            role="super_admin",
+            is_active=True,
+        )
+    )
+    await session.commit()
+
+
 async def init_db():
     import app.models.user  # noqa: F401
     import app.models.gpu_cluster  # noqa: F401
     import app.models.task  # noqa: F401
+    import app.models.data_snapshot  # noqa: F401
     import app.models.datasource  # noqa: F401
+    import app.models.datasource_config  # noqa: F401
+    import app.models.alert  # noqa: F401
+    import app.models.bgp_anomaly  # noqa: F401
+    import app.models.collected_data  # noqa: F401
+    import app.models.system_setting  # noqa: F401
 
     async with engine.begin() as conn:
         await conn.run_sync(Base.metadata.create_all)
+        await conn.execute(
+            text(
+                """
+                ALTER TABLE collected_data
+                ADD COLUMN IF NOT EXISTS snapshot_id INTEGER,
+                ADD COLUMN IF NOT EXISTS task_id INTEGER,
+                ADD COLUMN IF NOT EXISTS entity_key VARCHAR(255),
+                ADD COLUMN IF NOT EXISTS is_current BOOLEAN DEFAULT TRUE,
+                ADD COLUMN IF NOT EXISTS previous_record_id INTEGER,
+                ADD COLUMN IF NOT EXISTS change_type VARCHAR(20),
+                ADD COLUMN IF NOT EXISTS change_summary JSONB DEFAULT '{}'::jsonb,
+                ADD COLUMN IF NOT EXISTS deleted_at TIMESTAMPTZ
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                ALTER TABLE collection_tasks
+                ADD COLUMN IF NOT EXISTS phase VARCHAR(30) DEFAULT 'queued'
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                CREATE INDEX IF NOT EXISTS idx_collected_data_source_source_id
+                ON collected_data (source, source_id)
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                UPDATE collected_data
+                SET entity_key = source || ':' || COALESCE(source_id, id::text)
+                WHERE entity_key IS NULL
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                UPDATE collected_data
+                SET is_current = TRUE
+                WHERE is_current IS NULL
+                """
+            )
+        )
+
+    async with async_session_factory() as session:
+        await seed_default_datasources(session)
+        await ensure_default_admin_user(session)

backend/app/main.py

@@ -2,15 +2,19 @@ from contextlib import asynccontextmanager
 
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
-from fastapi.staticfiles import StaticFiles
 from starlette.middleware.base import BaseHTTPMiddleware
 
-from app.core.config import settings
-from app.core.websocket.broadcaster import broadcaster
-from app.db.session import init_db, async_session_factory
 from app.api.main import api_router
 from app.api.v1 import websocket
-from app.services.scheduler import start_scheduler, stop_scheduler
+from app.core.config import settings
+from app.core.websocket.broadcaster import broadcaster
+from app.db.session import init_db
+from app.services.scheduler import (
+    cleanup_stale_running_tasks,
+    start_scheduler,
+    stop_scheduler,
+    sync_scheduler_with_datasources,
+)
 
 
 class WebSocketCORSMiddleware(BaseHTTPMiddleware):
@@ -27,7 +31,9 @@ class WebSocketCORSMiddleware(BaseHTTPMiddleware):
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     await init_db()
+    await cleanup_stale_running_tasks()
     start_scheduler()
+    await sync_scheduler_with_datasources()
     broadcaster.start()
     yield
     broadcaster.stop()
@@ -60,16 +66,11 @@ app.include_router(websocket.router)
 
 @app.get("/health")
 async def health_check():
-    """健康检查端点"""
+    return {"status": "healthy", "version": settings.VERSION}
-    return {
-        "status": "healthy",
-        "version": settings.VERSION,
-    }
 
 
 @app.get("/")
 async def root():
-    """API根目录"""
     return {
         "name": settings.PROJECT_NAME,
         "version": settings.VERSION,
@@ -80,7 +81,6 @@ async def root():
 
 @app.get("/api/v1/scheduler/jobs")
 async def get_scheduler_jobs():
-    """获取调度任务列表"""
     from app.services.scheduler import get_scheduler_jobs
 
     return {"jobs": get_scheduler_jobs()}

backend/app/models/__init__.py

@@ -1,15 +1,23 @@
 from app.models.user import User
 from app.models.gpu_cluster import GPUCluster
 from app.models.task import CollectionTask
+from app.models.data_snapshot import DataSnapshot
 from app.models.datasource import DataSource
+from app.models.datasource_config import DataSourceConfig
 from app.models.alert import Alert, AlertSeverity, AlertStatus
+from app.models.bgp_anomaly import BGPAnomaly
+from app.models.system_setting import SystemSetting
 
 __all__ = [
     "User",
     "GPUCluster",
     "CollectionTask",
+    "DataSnapshot",
     "DataSource",
+    "DataSourceConfig",
+    "SystemSetting",
     "Alert",
     "AlertSeverity",
     "AlertStatus",
+    "BGPAnomaly",
 ]

backend/app/models/alert.py

@@ -5,6 +5,7 @@ from typing import Optional
 from sqlalchemy import Column, Integer, String, DateTime, Text, ForeignKey, Enum as SQLEnum
 from sqlalchemy.orm import relationship
 
+from app.core.time import to_iso8601_utc
 from app.db.session import Base
 
 
@@ -50,8 +51,8 @@ class Alert(Base):
             "acknowledged_by": self.acknowledged_by,
             "resolved_by": self.resolved_by,
             "resolution_notes": self.resolution_notes,
-            "created_at": self.created_at.isoformat() if self.created_at else None,
+            "created_at": to_iso8601_utc(self.created_at),
-            "updated_at": self.updated_at.isoformat() if self.updated_at else None,
+            "updated_at": to_iso8601_utc(self.updated_at),
-            "acknowledged_at": self.acknowledged_at.isoformat() if self.acknowledged_at else None,
+            "acknowledged_at": to_iso8601_utc(self.acknowledged_at),
-            "resolved_at": self.resolved_at.isoformat() if self.resolved_at else None,
+            "resolved_at": to_iso8601_utc(self.resolved_at),
         }

backend/app/models/bgp_anomaly.py

@@ -0,0 +1,58 @@
+"""BGP anomaly model for derived routing intelligence."""
+
+from datetime import datetime
+
+from sqlalchemy import Column, DateTime, Float, ForeignKey, Index, Integer, JSON, String, Text
+
+from app.core.time import to_iso8601_utc
+from app.db.session import Base
+
+
+class BGPAnomaly(Base):
+    __tablename__ = "bgp_anomalies"
+
+    id = Column(Integer, primary_key=True, index=True)
+    snapshot_id = Column(Integer, ForeignKey("data_snapshots.id"), nullable=True, index=True)
+    task_id = Column(Integer, ForeignKey("collection_tasks.id"), nullable=True, index=True)
+    source = Column(String(100), nullable=False, index=True)
+    anomaly_type = Column(String(50), nullable=False, index=True)
+    severity = Column(String(20), nullable=False, index=True)
+    status = Column(String(20), nullable=False, default="active", index=True)
+    entity_key = Column(String(255), nullable=False, index=True)
+    prefix = Column(String(64), nullable=True, index=True)
+    origin_asn = Column(Integer, nullable=True, index=True)
+    new_origin_asn = Column(Integer, nullable=True, index=True)
+    peer_scope = Column(JSON, default=list)
+    started_at = Column(DateTime(timezone=True), nullable=False, default=datetime.utcnow, index=True)
+    ended_at = Column(DateTime(timezone=True), nullable=True)
+    confidence = Column(Float, nullable=False, default=0.5)
+    summary = Column(Text, nullable=False)
+    evidence = Column(JSON, default=dict)
+    created_at = Column(DateTime(timezone=True), nullable=False, default=datetime.utcnow, index=True)
+
+    __table_args__ = (
+        Index("idx_bgp_anomalies_source_created", "source", "created_at"),
+        Index("idx_bgp_anomalies_type_status", "anomaly_type", "status"),
+    )
+
+    def to_dict(self) -> dict:
+        return {
+            "id": self.id,
+            "snapshot_id": self.snapshot_id,
+            "task_id": self.task_id,
+            "source": self.source,
+            "anomaly_type": self.anomaly_type,
+            "severity": self.severity,
+            "status": self.status,
+            "entity_key": self.entity_key,
+            "prefix": self.prefix,
+            "origin_asn": self.origin_asn,
+            "new_origin_asn": self.new_origin_asn,
+            "peer_scope": self.peer_scope or [],
+            "started_at": to_iso8601_utc(self.started_at),
+            "ended_at": to_iso8601_utc(self.ended_at),
+            "confidence": self.confidence,
+            "summary": self.summary,
+            "evidence": self.evidence or {},
+            "created_at": to_iso8601_utc(self.created_at),
+        }

backend/app/models/collected_data.py

@@ -1,8 +1,10 @@
 """Collected Data model for storing data from all collectors"""
 
-from sqlalchemy import Column, DateTime, Integer, String, Text, JSON, Index
+from sqlalchemy import Boolean, Column, DateTime, ForeignKey, Integer, String, Text, JSON, Index
 from sqlalchemy.sql import func
 
+from app.core.collected_data_fields import get_record_field
+from app.core.time import to_iso8601_utc
 from app.db.session import Base
 
 
@@ -12,8 +14,11 @@ class CollectedData(Base):
     __tablename__ = "collected_data"
 
     id = Column(Integer, primary_key=True, autoincrement=True)
+    snapshot_id = Column(Integer, ForeignKey("data_snapshots.id"), nullable=True, index=True)
+    task_id = Column(Integer, ForeignKey("collection_tasks.id"), nullable=True, index=True)
     source = Column(String(100), nullable=False, index=True)  # e.g., "top500", "huggingface_models"
     source_id = Column(String(100), index=True)  # Original ID from source, e.g., "rank_1"
+    entity_key = Column(String(255), index=True)
     data_type = Column(
         String(50), nullable=False, index=True
     )  # e.g., "supercomputer", "model", "dataset"
@@ -23,16 +28,6 @@ class CollectedData(Base):
     title = Column(String(500))
     description = Column(Text)
 
-    # Location data (for geo visualization)
-    country = Column(String(100))
-    city = Column(String(100))
-    latitude = Column(String(50))
-    longitude = Column(String(50))
-
-    # Performance metrics
-    value = Column(String(100))  # Generic value field (Rmax, Rpeak, etc.)
-    unit = Column(String(20))
-
     # Additional metadata as JSON
     extra_data = Column(
         "metadata", JSON, default={}
@@ -44,11 +39,17 @@ class CollectedData(Base):
 
     # Status
     is_valid = Column(Integer, default=1)  # 1=valid, 0=invalid
+    is_current = Column(Boolean, default=True, index=True)
+    previous_record_id = Column(Integer, ForeignKey("collected_data.id"), nullable=True, index=True)
+    change_type = Column(String(20), nullable=True)
+    change_summary = Column(JSON, default={})
+    deleted_at = Column(DateTime(timezone=True), nullable=True)
 
     # Indexes for common queries
     __table_args__ = (
         Index("idx_collected_data_source_collected", "source", "collected_at"),
         Index("idx_collected_data_source_type", "source", "data_type"),
+        Index("idx_collected_data_source_source_id", "source", "source_id"),
     )
 
     def __repr__(self):
@@ -58,23 +59,27 @@ class CollectedData(Base):
         """Convert to dictionary"""
         return {
             "id": self.id,
+            "snapshot_id": self.snapshot_id,
+            "task_id": self.task_id,
             "source": self.source,
             "source_id": self.source_id,
+            "entity_key": self.entity_key,
             "data_type": self.data_type,
             "name": self.name,
             "title": self.title,
             "description": self.description,
-            "country": self.country,
+            "country": get_record_field(self, "country"),
-            "city": self.city,
+            "city": get_record_field(self, "city"),
-            "latitude": self.latitude,
+            "latitude": get_record_field(self, "latitude"),
-            "longitude": self.longitude,
+            "longitude": get_record_field(self, "longitude"),
-            "value": self.value,
+            "value": get_record_field(self, "value"),
-            "unit": self.unit,
+            "unit": get_record_field(self, "unit"),
             "metadata": self.extra_data,
-            "collected_at": self.collected_at.isoformat()
+            "collected_at": to_iso8601_utc(self.collected_at),
-            if self.collected_at is not None
+            "reference_date": to_iso8601_utc(self.reference_date),
-            else None,
+            "is_current": self.is_current,
-            "reference_date": self.reference_date.isoformat()
+            "previous_record_id": self.previous_record_id,
-            if self.reference_date is not None
+            "change_type": self.change_type,
-            else None,
+            "change_summary": self.change_summary,
+            "deleted_at": to_iso8601_utc(self.deleted_at),
         }

backend/app/models/data_snapshot.py

@@ -0,0 +1,26 @@
+from sqlalchemy import Boolean, Column, DateTime, ForeignKey, Integer, JSON, String
+from sqlalchemy.sql import func
+
+from app.db.session import Base
+
+
+class DataSnapshot(Base):
+    __tablename__ = "data_snapshots"
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    datasource_id = Column(Integer, nullable=False, index=True)
+    task_id = Column(Integer, ForeignKey("collection_tasks.id"), nullable=True, index=True)
+    source = Column(String(100), nullable=False, index=True)
+    snapshot_key = Column(String(100), nullable=True, index=True)
+    reference_date = Column(DateTime(timezone=True), nullable=True)
+    started_at = Column(DateTime(timezone=True), server_default=func.now())
+    completed_at = Column(DateTime(timezone=True), nullable=True)
+    record_count = Column(Integer, default=0)
+    status = Column(String(20), nullable=False, default="running")
+    is_current = Column(Boolean, default=True, index=True)
+    parent_snapshot_id = Column(Integer, ForeignKey("data_snapshots.id"), nullable=True, index=True)
+    summary = Column(JSON, default={})
+    created_at = Column(DateTime(timezone=True), server_default=func.now())
+
+    def __repr__(self):
+        return f"<DataSnapshot {self.id}: {self.source}/{self.status}>"

backend/app/models/system_setting.py

@@ -0,0 +1,19 @@
+"""Persistent system settings model."""
+
+from sqlalchemy import JSON, Column, DateTime, Integer, String, UniqueConstraint
+from sqlalchemy.sql import func
+
+from app.db.session import Base
+
+
+class SystemSetting(Base):
+    __tablename__ = "system_settings"
+    __table_args__ = (UniqueConstraint("category", name="uq_system_settings_category"),)
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    category = Column(String(50), nullable=False)
+    payload = Column(JSON, nullable=False, default={})
+    updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
+
+    def __repr__(self):
+        return f"<SystemSetting {self.category}>"

backend/app/models/task.py

@@ -12,6 +12,7 @@ class CollectionTask(Base):
     id = Column(Integer, primary_key=True, autoincrement=True)
     datasource_id = Column(Integer, nullable=False, index=True)
     status = Column(String(20), nullable=False)  # pending, running, success, failed, cancelled
+    phase = Column(String(30), default="queued")
     started_at = Column(DateTime(timezone=True))
     completed_at = Column(DateTime(timezone=True))
     records_processed = Column(Integer, default=0)

backend/app/services/collectors/__init__.py

@@ -28,6 +28,10 @@ from app.services.collectors.arcgis_cables import ArcGISCableCollector
 from app.services.collectors.fao_landing import FAOLandingPointCollector
 from app.services.collectors.arcgis_landing import ArcGISLandingPointCollector
 from app.services.collectors.arcgis_relation import ArcGISCableLandingRelationCollector
+from app.services.collectors.spacetrack import SpaceTrackTLECollector
+from app.services.collectors.celestrak import CelesTrakTLECollector
+from app.services.collectors.ris_live import RISLiveCollector
+from app.services.collectors.bgpstream import BGPStreamBackfillCollector
 
 collector_registry.register(TOP500Collector())
 collector_registry.register(EpochAIGPUCollector())
@@ -47,3 +51,7 @@ collector_registry.register(ArcGISCableCollector())
 collector_registry.register(FAOLandingPointCollector())
 collector_registry.register(ArcGISLandingPointCollector())
 collector_registry.register(ArcGISCableLandingRelationCollector())
+collector_registry.register(SpaceTrackTLECollector())
+collector_registry.register(CelesTrakTLECollector())
+collector_registry.register(RISLiveCollector())
+collector_registry.register(BGPStreamBackfillCollector())

backend/app/services/collectors/arcgis_cables.py

@@ -5,10 +5,12 @@ Collects submarine cable data from ArcGIS GeoJSON API.
 
 import json
 from typing import Dict, Any, List
-from datetime import datetime
+from datetime import UTC, datetime
 import httpx
 
 from app.services.collectors.base import BaseCollector
+from app.core.data_sources import get_data_sources_config
+
 
 
 class ArcGISCableCollector(BaseCollector):
@@ -18,7 +20,14 @@ class ArcGISCableCollector(BaseCollector):
     frequency_hours = 168
     data_type = "submarine_cable"
 
-    base_url = "https://services.arcgis.com/6DIQcwlPy8knb6sg/arcgis/rest/services/SubmarineCables/FeatureServer/2/query"
+    @property
+    def base_url(self) -> str:
+        if self._resolved_url:
+            return self._resolved_url
+        from app.core.data_sources import get_data_sources_config
+
+        config = get_data_sources_config()
+        return config.get_yaml_url("arcgis_cables")
 
     async def fetch(self) -> List[Dict[str, Any]]:
         params = {"where": "1=1", "outFields": "*", "returnGeometry": "true", "f": "geojson"}
@@ -75,7 +84,7 @@ class ArcGISCableCollector(BaseCollector):
                         "color": props.get("color"),
                         "route_coordinates": route_coordinates,
                     },
-                    "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                    "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
                 }
                 result.append(entry)
             except (ValueError, TypeError, KeyError):

backend/app/services/collectors/arcgis_landing.py

@@ -1,12 +1,10 @@
-"""ArcGIS Landing Points Collector
-
-Collects landing point data from ArcGIS GeoJSON API.
-"""
-
 from typing import Dict, Any, List
-from datetime import datetime
+from datetime import UTC, datetime
+import httpx
 
 from app.services.collectors.base import BaseCollector
+from app.core.data_sources import get_data_sources_config
+
 
 
 class ArcGISLandingPointCollector(BaseCollector):
@@ -16,21 +14,23 @@ class ArcGISLandingPointCollector(BaseCollector):
     frequency_hours = 168
     data_type = "landing_point"
 
-    base_url = "https://services.arcgis.com/6DIQcwlPy8knb6sg/arcgis/rest/services/SubmarineCables/FeatureServer/1/query"
+    @property
+    def base_url(self) -> str:
+        if self._resolved_url:
+            return self._resolved_url
+        from app.core.data_sources import get_data_sources_config
+
+        config = get_data_sources_config()
+        return config.get_yaml_url("arcgis_landing_points")
 
     async def fetch(self) -> List[Dict[str, Any]]:
         params = {"where": "1=1", "outFields": "*", "returnGeometry": "true", "f": "geojson"}
 
-        async with self._get_client() as client:
+        async with httpx.AsyncClient(timeout=60.0) as client:
             response = await client.get(self.base_url, params=params)
             response.raise_for_status()
             return self.parse_response(response.json())
 
-    def _get_client(self):
-        import httpx
-
-        return httpx.AsyncClient(timeout=60.0)
-
     def parse_response(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
         result = []
 
@@ -39,6 +39,11 @@ class ArcGISLandingPointCollector(BaseCollector):
             props = feature.get("properties", {})
             geometry = feature.get("geometry", {})
 
+            if geometry.get("type") == "Point":
+                coords = geometry.get("coordinates", [])
+                lon = coords[0] if len(coords) > 0 else None
+                lat = coords[1] if len(coords) > 1 else None
+            else:
                 lat = geometry.get("y") if geometry else None
                 lon = geometry.get("x") if geometry else None
 
@@ -54,6 +59,7 @@ class ArcGISLandingPointCollector(BaseCollector):
                     "unit": "",
                     "metadata": {
                         "objectid": props.get("OBJECTID"),
+                        "city_id": props.get("city_id"),
                         "cable_id": props.get("cable_id"),
                         "cable_name": props.get("cable_name"),
                         "facility": props.get("facility"),
@@ -61,7 +67,7 @@ class ArcGISLandingPointCollector(BaseCollector):
                         "status": props.get("status"),
                         "landing_point_id": props.get("landing_point_id"),
                     },
-                    "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                    "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
                 }
                 result.append(entry)
             except (ValueError, TypeError, KeyError):

backend/app/services/collectors/arcgis_relation.py

@@ -1,6 +1,10 @@
-from typing import Dict, Any, List
+import asyncio
-from datetime import datetime
+from datetime import UTC, datetime
+from typing import Any, Dict, List, Optional
 
+import httpx
+
+from app.core.data_sources import get_data_sources_config
 from app.services.collectors.base import BaseCollector
 
 
@@ -11,45 +15,135 @@ class ArcGISCableLandingRelationCollector(BaseCollector):
     frequency_hours = 168
     data_type = "cable_landing_relation"
 
-    base_url = "https://services.arcgis.com/6DIQcwlPy8knb6sg/arcgis/rest/services/SubmarineCables/FeatureServer/3/query"
+    @property
+    def base_url(self) -> str:
+        if self._resolved_url:
+            return self._resolved_url
+        config = get_data_sources_config()
+        return config.get_yaml_url("arcgis_cable_landing_relation")
+
+    def _layer_url(self, layer_id: int) -> str:
+        if "/FeatureServer/" not in self.base_url:
+            return self.base_url
+        prefix = self.base_url.split("/FeatureServer/")[0]
+        return f"{prefix}/FeatureServer/{layer_id}/query"
+
+    async def _fetch_layer_attributes(
+        self, client: httpx.AsyncClient, layer_id: int
+    ) -> List[Dict[str, Any]]:
+        response = await client.get(
+            self._layer_url(layer_id),
+            params={
+                "where": "1=1",
+                "outFields": "*",
+                "returnGeometry": "false",
+                "f": "json",
+            },
+        )
+        response.raise_for_status()
+        data = response.json()
+        return [feature.get("attributes", {}) for feature in data.get("features", [])]
+
+    async def _fetch_relation_features(self, client: httpx.AsyncClient) -> List[Dict[str, Any]]:
+        response = await client.get(
+            self.base_url,
+            params={
+                "where": "1=1",
+                "outFields": "*",
+                "returnGeometry": "true",
+                "f": "geojson",
+            },
+        )
+        response.raise_for_status()
+        data = response.json()
+        return data.get("features", [])
 
     async def fetch(self) -> List[Dict[str, Any]]:
-        import httpx
-
-        params = {"where": "1=1", "outFields": "*", "returnGeometry": "true", "f": "geojson"}
-
         async with httpx.AsyncClient(timeout=60.0) as client:
-            response = await client.get(self.base_url, params=params)
+            relation_features, landing_rows, cable_rows = await asyncio.gather(
-            response.raise_for_status()
+                self._fetch_relation_features(client),
-            return self.parse_response(response.json())
+                self._fetch_layer_attributes(client, 1),
+                self._fetch_layer_attributes(client, 2),
+            )
+        return self.parse_response(relation_features, landing_rows, cable_rows)
 
-    def parse_response(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
+    def _build_landing_lookup(self, landing_rows: List[Dict[str, Any]]) -> Dict[int, Dict[str, Any]]:
-        result = []
+        lookup: Dict[int, Dict[str, Any]] = {}
+        for row in landing_rows:
+            city_id = row.get("city_id")
+            if city_id is None:
+                continue
+            lookup[int(city_id)] = {
+                "landing_point_id": row.get("landing_point_id") or city_id,
+                "landing_point_name": row.get("Name") or row.get("name") or "",
+                "facility": row.get("facility") or "",
+                "status": row.get("status") or "",
+                "country": row.get("country") or "",
+            }
+        return lookup
 
-        features = data.get("features", [])
+    def _build_cable_lookup(self, cable_rows: List[Dict[str, Any]]) -> Dict[int, Dict[str, Any]]:
-        for feature in features:
+        lookup: Dict[int, Dict[str, Any]] = {}
+        for row in cable_rows:
+            cable_id = row.get("cable_id")
+            if cable_id is None:
+                continue
+            lookup[int(cable_id)] = {
+                "cable_name": row.get("Name") or "",
+                "status": row.get("status") or "active",
+            }
+        return lookup
+
+    def parse_response(
+        self,
+        relation_features: List[Dict[str, Any]],
+        landing_rows: List[Dict[str, Any]],
+        cable_rows: List[Dict[str, Any]],
+    ) -> List[Dict[str, Any]]:
+        result: List[Dict[str, Any]] = []
+        landing_lookup = self._build_landing_lookup(landing_rows)
+        cable_lookup = self._build_cable_lookup(cable_rows)
+
+        for feature in relation_features:
             props = feature.get("properties", {})
 
             try:
+                city_id = props.get("city_id")
+                cable_id = props.get("cable_id")
+                landing_info = landing_lookup.get(int(city_id), {}) if city_id is not None else {}
+                cable_info = cable_lookup.get(int(cable_id), {}) if cable_id is not None else {}
+
+                cable_name = cable_info.get("cable_name") or props.get("cable_name") or "Unknown"
+                landing_point_name = (
+                    landing_info.get("landing_point_name")
+                    or props.get("landing_point_name")
+                    or "Unknown"
+                )
+                facility = landing_info.get("facility") or props.get("facility") or "-"
+                status = cable_info.get("status") or landing_info.get("status") or props.get("status") or "-"
+                country = landing_info.get("country") or props.get("country") or ""
+                landing_point_id = landing_info.get("landing_point_id") or props.get("landing_point_id") or city_id
+
                 entry = {
                     "source_id": f"arcgis_relation_{props.get('OBJECTID', props.get('id', ''))}",
-                    "name": f"{props.get('cable_name', 'Unknown')} - {props.get('landing_point_name', 'Unknown')}",
+                    "name": f"{cable_name} - {landing_point_name}",
-                    "country": props.get("country", ""),
+                    "country": country,
-                    "city": props.get("landing_point_name", ""),
+                    "city": landing_point_name,
                     "latitude": str(props.get("latitude", "")) if props.get("latitude") else "",
                     "longitude": str(props.get("longitude", "")) if props.get("longitude") else "",
                     "value": "",
                     "unit": "",
                     "metadata": {
                         "objectid": props.get("OBJECTID"),
-                        "cable_id": props.get("cable_id"),
+                        "city_id": city_id,
-                        "cable_name": props.get("cable_name"),
+                        "cable_id": cable_id,
-                        "landing_point_id": props.get("landing_point_id"),
+                        "cable_name": cable_name,
-                        "landing_point_name": props.get("landing_point_name"),
+                        "landing_point_id": landing_point_id,
-                        "facility": props.get("facility"),
+                        "landing_point_name": landing_point_name,
-                        "status": props.get("status"),
+                        "facility": facility,
+                        "status": status,
                     },
-                    "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                    "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
                 }
                 result.append(entry)
             except (ValueError, TypeError, KeyError):

backend/app/services/collectors/base.py

@@ -2,12 +2,16 @@
 
 from abc import ABC, abstractmethod
 from typing import Dict, List, Any, Optional
-from datetime import datetime
+from datetime import UTC, datetime
 import httpx
-from sqlalchemy import text
+from sqlalchemy import select, text
 from sqlalchemy.ext.asyncio import AsyncSession
 
+from app.core.collected_data_fields import build_dynamic_metadata, get_record_field
 from app.core.config import settings
+from app.core.countries import normalize_country
+from app.core.time import to_iso8601_utc
+from app.core.websocket.broadcaster import broadcaster
 
 
 class BaseCollector(ABC):
@@ -18,19 +22,68 @@ class BaseCollector(ABC):
     module: str = "L1"
     frequency_hours: int = 4
     data_type: str = "generic"
+    fail_on_empty: bool = False
 
     def __init__(self):
         self._current_task = None
         self._db_session = None
         self._datasource_id = 1
+        self._resolved_url: Optional[str] = None
+        self._last_broadcast_progress: Optional[int] = None
 
-    def update_progress(self, records_processed: int):
+    async def resolve_url(self, db: AsyncSession) -> None:
+        from app.core.data_sources import get_data_sources_config
+
+        config = get_data_sources_config()
+        self._resolved_url = await config.get_url(self.name, db)
+
+    async def _publish_task_update(self, force: bool = False):
+        if not self._current_task:
+            return
+
+        progress = float(self._current_task.progress or 0.0)
+        rounded_progress = int(round(progress))
+        if not force and self._last_broadcast_progress == rounded_progress:
+            return
+
+        await broadcaster.broadcast_datasource_task_update(
+            {
+                "datasource_id": getattr(self, "_datasource_id", None),
+                "collector_name": self.name,
+                "task_id": self._current_task.id,
+                "status": self._current_task.status,
+                "phase": self._current_task.phase,
+                "progress": progress,
+                "records_processed": self._current_task.records_processed,
+                "total_records": self._current_task.total_records,
+                "started_at": to_iso8601_utc(self._current_task.started_at),
+                "completed_at": to_iso8601_utc(self._current_task.completed_at),
+                "error_message": self._current_task.error_message,
+            }
+        )
+        self._last_broadcast_progress = rounded_progress
+
+    async def update_progress(self, records_processed: int, *, commit: bool = False, force: bool = False):
         """Update task progress - call this during data processing"""
-        if self._current_task and self._db_session and self._current_task.total_records > 0:
+        if self._current_task and self._db_session:
             self._current_task.records_processed = records_processed
+            if self._current_task.total_records and self._current_task.total_records > 0:
                 self._current_task.progress = (
                     records_processed / self._current_task.total_records
                 ) * 100
+            else:
+                self._current_task.progress = 0.0
+
+            if commit:
+                await self._db_session.commit()
+
+            await self._publish_task_update(force=force)
+
+    async def set_phase(self, phase: str):
+        if self._current_task and self._db_session:
+            self._current_task.phase = phase
+            await self._db_session.commit()
+            await self._publish_task_update(force=True)
 
     @abstractmethod
     async def fetch(self) -> List[Dict[str, Any]]:
@@ -41,14 +94,87 @@ class BaseCollector(ABC):
         """Transform raw data to internal format (default: pass through)"""
         return raw_data
 
+    def _parse_reference_date(self, value: Any) -> Optional[datetime]:
+        if not value:
+            return None
+        if isinstance(value, datetime):
+            return value
+        if isinstance(value, str):
+            return datetime.fromisoformat(value.replace("Z", "+00:00"))
+        return None
+
+    def _build_comparable_payload(self, record: Any) -> Dict[str, Any]:
+        return {
+            "name": getattr(record, "name", None),
+            "title": getattr(record, "title", None),
+            "description": getattr(record, "description", None),
+            "country": get_record_field(record, "country"),
+            "city": get_record_field(record, "city"),
+            "latitude": get_record_field(record, "latitude"),
+            "longitude": get_record_field(record, "longitude"),
+            "value": get_record_field(record, "value"),
+            "unit": get_record_field(record, "unit"),
+            "metadata": getattr(record, "extra_data", None) or {},
+            "reference_date": (
+                getattr(record, "reference_date", None).isoformat()
+                if getattr(record, "reference_date", None)
+                else None
+            ),
+        }
+
+    async def _create_snapshot(
+        self,
+        db: AsyncSession,
+        task_id: int,
+        data: List[Dict[str, Any]],
+        started_at: datetime,
+    ) -> int:
+        from app.models.data_snapshot import DataSnapshot
+
+        reference_dates = [
+            parsed
+            for parsed in (self._parse_reference_date(item.get("reference_date")) for item in data)
+            if parsed is not None
+        ]
+        reference_date = max(reference_dates) if reference_dates else None
+
+        result = await db.execute(
+            select(DataSnapshot)
+            .where(DataSnapshot.source == self.name, DataSnapshot.is_current == True)
+            .order_by(DataSnapshot.completed_at.desc().nullslast(), DataSnapshot.id.desc())
+            .limit(1)
+        )
+        previous_snapshot = result.scalar_one_or_none()
+
+        snapshot = DataSnapshot(
+            datasource_id=getattr(self, "_datasource_id", 1),
+            task_id=task_id,
+            source=self.name,
+            snapshot_key=f"{self.name}:{task_id}",
+            reference_date=reference_date,
+            started_at=started_at,
+            status="running",
+            is_current=True,
+            parent_snapshot_id=previous_snapshot.id if previous_snapshot else None,
+            summary={},
+        )
+        db.add(snapshot)
+
+        if previous_snapshot:
+            previous_snapshot.is_current = False
+
+        await db.commit()
+        return snapshot.id
+
     async def run(self, db: AsyncSession) -> Dict[str, Any]:
         """Full pipeline: fetch -> transform -> save"""
         from app.services.collectors.registry import collector_registry
         from app.models.task import CollectionTask
-        from app.models.collected_data import CollectedData
+        from app.models.data_snapshot import DataSnapshot
 
-        start_time = datetime.utcnow()
+        start_time = datetime.now(UTC)
         datasource_id = getattr(self, "_datasource_id", 1)
+        snapshot_id: Optional[int] = None
 
         if not collector_registry.is_active(self.name):
             return {"status": "skipped", "reason": "Collector is disabled"}
@@ -56,6 +182,7 @@ class BaseCollector(ABC):
         task = CollectionTask(
             datasource_id=datasource_id,
             status="running",
+            phase="queued",
             started_at=start_time,
         )
         db.add(task)
@@ -64,88 +191,221 @@ class BaseCollector(ABC):
 
         self._current_task = task
         self._db_session = db
+        self._last_broadcast_progress = None
+
+        await self.resolve_url(db)
+        await self._publish_task_update(force=True)
 
         try:
+            await self.set_phase("fetching")
             raw_data = await self.fetch()
             task.total_records = len(raw_data)
             await db.commit()
+            await self._publish_task_update(force=True)
 
+            if self.fail_on_empty and not raw_data:
+                raise RuntimeError(f"Collector {self.name} returned no data")
+
+            await self.set_phase("transforming")
             data = self.transform(raw_data)
+            snapshot_id = await self._create_snapshot(db, task_id, data, start_time)
 
-            records_count = await self._save_data(db, data)
+            await self.set_phase("saving")
+            records_count = await self._save_data(db, data, task_id=task_id, snapshot_id=snapshot_id)
 
             task.status = "success"
+            task.phase = "completed"
             task.records_processed = records_count
             task.progress = 100.0
-            task.completed_at = datetime.utcnow()
+            task.completed_at = datetime.now(UTC)
             await db.commit()
+            await self._publish_task_update(force=True)
 
             return {
                 "status": "success",
                 "task_id": task_id,
                 "records_processed": records_count,
-                "execution_time_seconds": (datetime.utcnow() - start_time).total_seconds(),
+                "execution_time_seconds": (datetime.now(UTC) - start_time).total_seconds(),
             }
         except Exception as e:
-            # Log task failure
             task.status = "failed"
+            task.phase = "failed"
             task.error_message = str(e)
-            task.completed_at = datetime.utcnow()
+            task.completed_at = datetime.now(UTC)
+            if snapshot_id is not None:
+                snapshot = await db.get(DataSnapshot, snapshot_id)
+                if snapshot:
+                    snapshot.status = "failed"
+                    snapshot.completed_at = datetime.now(UTC)
+                    snapshot.summary = {"error": str(e)}
             await db.commit()
+            await self._publish_task_update(force=True)
 
             return {
                 "status": "failed",
                 "task_id": task_id,
                 "error": str(e),
-                "execution_time_seconds": (datetime.utcnow() - start_time).total_seconds(),
+                "execution_time_seconds": (datetime.now(UTC) - start_time).total_seconds(),
             }
 
-    async def _save_data(self, db: AsyncSession, data: List[Dict[str, Any]]) -> int:
+    async def _save_data(
+        self,
+        db: AsyncSession,
+        data: List[Dict[str, Any]],
+        task_id: Optional[int] = None,
+        snapshot_id: Optional[int] = None,
+    ) -> int:
         """Save transformed data to database"""
         from app.models.collected_data import CollectedData
+        from app.models.data_snapshot import DataSnapshot
 
         if not data:
+            if snapshot_id is not None:
+                snapshot = await db.get(DataSnapshot, snapshot_id)
+                if snapshot:
+                    snapshot.record_count = 0
+                    snapshot.summary = {"created": 0, "updated": 0, "unchanged": 0}
+                    snapshot.status = "success"
+                    snapshot.completed_at = datetime.now(UTC)
+                    await db.commit()
             return 0
 
-        collected_at = datetime.utcnow()
+        collected_at = datetime.now(UTC)
         records_added = 0
+        created_count = 0
+        updated_count = 0
+        unchanged_count = 0
+        seen_entity_keys: set[str] = set()
+        previous_current_keys: set[str] = set()
+
+        previous_current_result = await db.execute(
+            select(CollectedData.entity_key).where(
+                CollectedData.source == self.name,
+                CollectedData.is_current == True,
+            )
+        )
+        previous_current_keys = {row[0] for row in previous_current_result.fetchall() if row[0]}
 
         for i, item in enumerate(data):
+            print(
+                f"DEBUG: Saving item {i}: name={item.get('name')}, metadata={item.get('metadata', 'NOT FOUND')}"
+            )
+            raw_metadata = item.get("metadata", {})
+            extra_data = build_dynamic_metadata(
+                raw_metadata,
+                country=item.get("country"),
+                city=item.get("city"),
+                latitude=item.get("latitude"),
+                longitude=item.get("longitude"),
+                value=item.get("value"),
+                unit=item.get("unit"),
+            )
+            normalized_country = normalize_country(item.get("country"))
+            if normalized_country is not None:
+                extra_data["country"] = normalized_country
+
+            if item.get("country") and normalized_country != item.get("country"):
+                extra_data["raw_country"] = item.get("country")
+                if normalized_country is None:
+                    extra_data["country_validation"] = "invalid"
+
+            source_id = item.get("source_id") or item.get("id")
+            reference_date = (
+                self._parse_reference_date(item.get("reference_date"))
+            )
+            source_id_str = str(source_id) if source_id is not None else None
+            entity_key = f"{self.name}:{source_id_str}" if source_id_str else f"{self.name}:{i}"
+            previous_record = None
+
+            if entity_key and entity_key not in seen_entity_keys:
+                result = await db.execute(
+                    select(CollectedData)
+                    .where(
+                        CollectedData.source == self.name,
+                        CollectedData.entity_key == entity_key,
+                        CollectedData.is_current == True,
+                    )
+                    .order_by(CollectedData.collected_at.desc().nullslast(), CollectedData.id.desc())
+                )
+                previous_records = result.scalars().all()
+                if previous_records:
+                    previous_record = previous_records[0]
+                    for old_record in previous_records:
+                        old_record.is_current = False
+
             record = CollectedData(
+                snapshot_id=snapshot_id,
+                task_id=task_id,
                 source=self.name,
-                source_id=item.get("source_id") or item.get("id"),
+                source_id=source_id_str,
+                entity_key=entity_key,
                 data_type=self.data_type,
                 name=item.get("name"),
                 title=item.get("title"),
                 description=item.get("description"),
-                country=item.get("country"),
+                extra_data=extra_data,
-                city=item.get("city"),
-                latitude=str(item.get("latitude", ""))
-                if item.get("latitude") is not None
-                else None,
-                longitude=str(item.get("longitude", ""))
-                if item.get("longitude") is not None
-                else None,
-                value=item.get("value"),
-                unit=item.get("unit"),
-                extra_data=item.get("metadata", {}),
                 collected_at=collected_at,
-                reference_date=datetime.fromisoformat(
+                reference_date=reference_date,
-                    item.get("reference_date").replace("Z", "+00:00")
-                )
-                if item.get("reference_date")
-                else None,
                 is_valid=1,
+                is_current=True,
+                previous_record_id=previous_record.id if previous_record else None,
+                deleted_at=None,
             )
+
+            if previous_record is None:
+                record.change_type = "created"
+                record.change_summary = {}
+                created_count += 1
+            else:
+                previous_payload = self._build_comparable_payload(previous_record)
+                current_payload = self._build_comparable_payload(record)
+                if current_payload == previous_payload:
+                    record.change_type = "unchanged"
+                    record.change_summary = {}
+                    unchanged_count += 1
+                else:
+                    changed_fields = [
+                        key for key in current_payload.keys() if current_payload[key] != previous_payload.get(key)
+                    ]
+                    record.change_type = "updated"
+                    record.change_summary = {"changed_fields": changed_fields}
+                    updated_count += 1
+
             db.add(record)
+            seen_entity_keys.add(entity_key)
             records_added += 1
 
             if i % 100 == 0:
-                self.update_progress(i + 1)
+                await self.update_progress(i + 1, commit=True)
-                await db.commit()
+
+        if snapshot_id is not None:
+            deleted_keys = previous_current_keys - seen_entity_keys
+            await db.execute(
+                text(
+                    """
+                    UPDATE collected_data
+                    SET is_current = FALSE
+                    WHERE source = :source
+                      AND snapshot_id IS DISTINCT FROM :snapshot_id
+                      AND COALESCE(is_current, TRUE) = TRUE
+                    """
+                ),
+                {"source": self.name, "snapshot_id": snapshot_id},
+            )
+            snapshot = await db.get(DataSnapshot, snapshot_id)
+            if snapshot:
+                snapshot.record_count = records_added
+                snapshot.status = "success"
+                snapshot.completed_at = datetime.now(UTC)
+                snapshot.summary = {
+                    "created": created_count,
+                    "updated": updated_count,
+                    "unchanged": unchanged_count,
+                    "deleted": len(deleted_keys),
+                }
 
         await db.commit()
-        self.update_progress(len(data))
+        await self.update_progress(len(data), force=True)
         return records_added
 
     async def save(self, db: AsyncSession, data: List[Dict[str, Any]]) -> int:
@@ -192,8 +452,8 @@ async def log_task(
         status=status,
         records_processed=records_processed,
         error_message=error_message,
-        started_at=datetime.utcnow(),
+        started_at=datetime.now(UTC),
-        completed_at=datetime.utcnow(),
+        completed_at=datetime.now(UTC),
     )
     db.add(task)
     await db.commit()

backend/app/services/collectors/bgp_common.py

@@ -0,0 +1,313 @@
+"""Shared helpers for BGP collectors."""
+
+from __future__ import annotations
+
+import hashlib
+import ipaddress
+from collections import Counter, defaultdict
+from datetime import UTC, datetime
+from typing import Any
+
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.models.bgp_anomaly import BGPAnomaly
+from app.models.collected_data import CollectedData
+
+
+RIPE_RIS_COLLECTOR_COORDS: dict[str, dict[str, Any]] = {
+    "rrc00": {"city": "Amsterdam", "country": "Netherlands", "latitude": 52.3676, "longitude": 4.9041},
+    "rrc01": {"city": "London", "country": "United Kingdom", "latitude": 51.5072, "longitude": -0.1276},
+    "rrc03": {"city": "Amsterdam", "country": "Netherlands", "latitude": 52.3676, "longitude": 4.9041},
+    "rrc04": {"city": "Geneva", "country": "Switzerland", "latitude": 46.2044, "longitude": 6.1432},
+    "rrc05": {"city": "Vienna", "country": "Austria", "latitude": 48.2082, "longitude": 16.3738},
+    "rrc06": {"city": "Otemachi", "country": "Japan", "latitude": 35.686, "longitude": 139.7671},
+    "rrc07": {"city": "Stockholm", "country": "Sweden", "latitude": 59.3293, "longitude": 18.0686},
+    "rrc10": {"city": "Milan", "country": "Italy", "latitude": 45.4642, "longitude": 9.19},
+    "rrc11": {"city": "New York", "country": "United States", "latitude": 40.7128, "longitude": -74.006},
+    "rrc12": {"city": "Frankfurt", "country": "Germany", "latitude": 50.1109, "longitude": 8.6821},
+    "rrc13": {"city": "Moscow", "country": "Russia", "latitude": 55.7558, "longitude": 37.6173},
+    "rrc14": {"city": "Palo Alto", "country": "United States", "latitude": 37.4419, "longitude": -122.143},
+    "rrc15": {"city": "Sao Paulo", "country": "Brazil", "latitude": -23.5558, "longitude": -46.6396},
+    "rrc16": {"city": "Miami", "country": "United States", "latitude": 25.7617, "longitude": -80.1918},
+    "rrc18": {"city": "Barcelona", "country": "Spain", "latitude": 41.3874, "longitude": 2.1686},
+    "rrc19": {"city": "Johannesburg", "country": "South Africa", "latitude": -26.2041, "longitude": 28.0473},
+    "rrc20": {"city": "Zurich", "country": "Switzerland", "latitude": 47.3769, "longitude": 8.5417},
+    "rrc21": {"city": "Paris", "country": "France", "latitude": 48.8566, "longitude": 2.3522},
+    "rrc22": {"city": "Bucharest", "country": "Romania", "latitude": 44.4268, "longitude": 26.1025},
+    "rrc23": {"city": "Singapore", "country": "Singapore", "latitude": 1.3521, "longitude": 103.8198},
+    "rrc24": {"city": "Montevideo", "country": "Uruguay", "latitude": -34.9011, "longitude": -56.1645},
+    "rrc25": {"city": "Amsterdam", "country": "Netherlands", "latitude": 52.3676, "longitude": 4.9041},
+    "rrc26": {"city": "Dubai", "country": "United Arab Emirates", "latitude": 25.2048, "longitude": 55.2708},
+}
+
+
+def _safe_int(value: Any) -> int | None:
+    try:
+        if value in (None, ""):
+            return None
+        return int(value)
+    except (TypeError, ValueError):
+        return None
+
+
+def _parse_timestamp(value: Any) -> datetime:
+    if isinstance(value, datetime):
+        return value.astimezone(UTC) if value.tzinfo else value.replace(tzinfo=UTC)
+
+    if isinstance(value, (int, float)):
+        return datetime.fromtimestamp(value, tz=UTC)
+
+    if isinstance(value, str) and value:
+        normalized = value.replace("Z", "+00:00")
+        parsed = datetime.fromisoformat(normalized)
+        return parsed.astimezone(UTC) if parsed.tzinfo else parsed.replace(tzinfo=UTC)
+
+    return datetime.now(UTC)
+
+
+def _normalize_as_path(raw_path: Any) -> list[int]:
+    if raw_path in (None, ""):
+        return []
+    if isinstance(raw_path, list):
+        return [asn for asn in (_safe_int(item) for item in raw_path) if asn is not None]
+    if isinstance(raw_path, str):
+        parts = raw_path.replace("{", "").replace("}", "").split()
+        return [asn for asn in (_safe_int(item) for item in parts) if asn is not None]
+    return []
+
+
+def normalize_bgp_event(payload: dict[str, Any], *, project: str) -> dict[str, Any]:
+    raw_message = payload.get("raw_message", payload)
+    raw_path = (
+        payload.get("path")
+        or payload.get("as_path")
+        or payload.get("attrs", {}).get("path")
+        or payload.get("attrs", {}).get("as_path")
+        or []
+    )
+    as_path = _normalize_as_path(raw_path)
+
+    raw_type = str(payload.get("event_type") or payload.get("type") or payload.get("msg_type") or "").lower()
+    if raw_type in {"a", "announce", "announcement"}:
+        event_type = "announcement"
+    elif raw_type in {"w", "withdraw", "withdrawal"}:
+        event_type = "withdrawal"
+    elif raw_type in {"r", "rib"}:
+        event_type = "rib"
+    else:
+        event_type = raw_type or "announcement"
+
+    prefix = str(payload.get("prefix") or payload.get("prefixes") or payload.get("target_prefix") or "").strip()
+    if prefix.startswith("[") and prefix.endswith("]"):
+        prefix = prefix[1:-1]
+
+    timestamp = _parse_timestamp(payload.get("timestamp") or payload.get("time") or payload.get("ts"))
+    collector = str(payload.get("collector") or payload.get("host") or payload.get("router") or "unknown")
+    peer_asn = _safe_int(payload.get("peer_asn") or payload.get("peer"))
+    origin_asn = _safe_int(payload.get("origin_asn")) or (as_path[-1] if as_path else None)
+    source_material = "|".join(
+        [
+            collector,
+            str(peer_asn or ""),
+            prefix,
+            event_type,
+            timestamp.isoformat(),
+            ",".join(str(asn) for asn in as_path),
+        ]
+    )
+    source_id = hashlib.sha1(source_material.encode("utf-8")).hexdigest()[:24]
+
+    prefix_length = None
+    is_more_specific = False
+    if prefix:
+        try:
+            network = ipaddress.ip_network(prefix, strict=False)
+            prefix_length = int(network.prefixlen)
+            is_more_specific = prefix_length > (24 if network.version == 4 else 48)
+        except ValueError:
+            prefix_length = None
+
+    collector_location = RIPE_RIS_COLLECTOR_COORDS.get(collector, {})
+    metadata = {
+        "project": project,
+        "collector": collector,
+        "peer_asn": peer_asn,
+        "peer_ip": payload.get("peer_ip") or payload.get("peer_address"),
+        "event_type": event_type,
+        "prefix": prefix,
+        "origin_asn": origin_asn,
+        "as_path": as_path,
+        "communities": payload.get("communities") or payload.get("attrs", {}).get("communities") or [],
+        "next_hop": payload.get("next_hop") or payload.get("attrs", {}).get("next_hop"),
+        "med": payload.get("med") or payload.get("attrs", {}).get("med"),
+        "local_pref": payload.get("local_pref") or payload.get("attrs", {}).get("local_pref"),
+        "timestamp": timestamp.isoformat(),
+        "as_path_length": len(as_path),
+        "prefix_length": prefix_length,
+        "is_more_specific": is_more_specific,
+        "visibility_weight": 1,
+        "collector_location": collector_location,
+        "raw_message": raw_message,
+    }
+
+    return {
+        "source_id": source_id,
+        "name": prefix or f"{collector}:{event_type}",
+        "title": f"{event_type} {prefix}".strip(),
+        "description": f"{collector} observed {event_type} for {prefix}".strip(),
+        "reference_date": timestamp.isoformat(),
+        "country": collector_location.get("country"),
+        "city": collector_location.get("city"),
+        "latitude": collector_location.get("latitude"),
+        "longitude": collector_location.get("longitude"),
+        "metadata": metadata,
+    }
+
+
+async def create_bgp_anomalies_for_batch(
+    db: AsyncSession,
+    *,
+    source: str,
+    snapshot_id: int | None,
+    task_id: int | None,
+    events: list[dict[str, Any]],
+) -> int:
+    if not events:
+        return 0
+
+    pending_anomalies: list[BGPAnomaly] = []
+    prefix_to_origins: defaultdict[str, set[int]] = defaultdict(set)
+    prefix_to_more_specifics: defaultdict[str, list[dict[str, Any]]] = defaultdict(list)
+    withdrawal_counter: Counter[tuple[str, int | None]] = Counter()
+
+    prefixes = {event["metadata"].get("prefix") for event in events if event.get("metadata", {}).get("prefix")}
+    previous_origin_map: dict[str, set[int]] = defaultdict(set)
+
+    if prefixes:
+        previous_query = await db.execute(
+            select(CollectedData).where(
+                CollectedData.source == source,
+                CollectedData.snapshot_id != snapshot_id,
+                CollectedData.extra_data["prefix"].as_string().in_(sorted(prefixes)),
+            )
+        )
+        for record in previous_query.scalars().all():
+            metadata = record.extra_data or {}
+            prefix = metadata.get("prefix")
+            origin = _safe_int(metadata.get("origin_asn"))
+            if prefix and origin is not None:
+                previous_origin_map[prefix].add(origin)
+
+    for event in events:
+        metadata = event.get("metadata", {})
+        prefix = metadata.get("prefix")
+        origin_asn = _safe_int(metadata.get("origin_asn"))
+        if not prefix:
+            continue
+
+        if origin_asn is not None:
+            prefix_to_origins[prefix].add(origin_asn)
+
+        if metadata.get("is_more_specific"):
+            prefix_to_more_specifics[prefix.split("/")[0]].append(event)
+
+        if metadata.get("event_type") == "withdrawal":
+            withdrawal_counter[(prefix, origin_asn)] += 1
+
+    for prefix, origins in prefix_to_origins.items():
+        historic = previous_origin_map.get(prefix, set())
+        new_origins = sorted(origin for origin in origins if origin not in historic)
+        if historic and new_origins:
+            for new_origin in new_origins:
+                pending_anomalies.append(
+                    BGPAnomaly(
+                    snapshot_id=snapshot_id,
+                    task_id=task_id,
+                    source=source,
+                    anomaly_type="origin_change",
+                    severity="critical",
+                    status="active",
+                    entity_key=f"origin_change:{prefix}:{new_origin}",
+                    prefix=prefix,
+                    origin_asn=sorted(historic)[0],
+                    new_origin_asn=new_origin,
+                    peer_scope=[],
+                    started_at=datetime.now(UTC),
+                    confidence=0.86,
+                    summary=f"Prefix {prefix} is now originated by AS{new_origin}, outside the current baseline.",
+                    evidence={"previous_origins": sorted(historic), "current_origins": sorted(origins)},
+                )
+                )
+
+    for root_prefix, more_specifics in prefix_to_more_specifics.items():
+        if len(more_specifics) >= 2:
+            sample = more_specifics[0]["metadata"]
+            pending_anomalies.append(
+                BGPAnomaly(
+                snapshot_id=snapshot_id,
+                task_id=task_id,
+                source=source,
+                anomaly_type="more_specific_burst",
+                severity="high",
+                status="active",
+                entity_key=f"more_specific_burst:{root_prefix}:{len(more_specifics)}",
+                prefix=sample.get("prefix"),
+                origin_asn=_safe_int(sample.get("origin_asn")),
+                new_origin_asn=None,
+                peer_scope=sorted(
+                    {
+                        str(item.get("metadata", {}).get("collector") or "")
+                        for item in more_specifics
+                        if item.get("metadata", {}).get("collector")
+                    }
+                ),
+                started_at=datetime.now(UTC),
+                confidence=0.72,
+                summary=f"{len(more_specifics)} more-specific announcements clustered around {root_prefix}.",
+                evidence={"events": [item.get("metadata") for item in more_specifics[:10]]},
+            )
+            )
+
+    for (prefix, origin_asn), count in withdrawal_counter.items():
+        if count >= 3:
+            pending_anomalies.append(
+                BGPAnomaly(
+                snapshot_id=snapshot_id,
+                task_id=task_id,
+                source=source,
+                anomaly_type="mass_withdrawal",
+                severity="high" if count < 8 else "critical",
+                status="active",
+                entity_key=f"mass_withdrawal:{prefix}:{origin_asn}:{count}",
+                prefix=prefix,
+                origin_asn=origin_asn,
+                new_origin_asn=None,
+                peer_scope=[],
+                started_at=datetime.now(UTC),
+                confidence=min(0.55 + (count * 0.05), 0.95),
+                summary=f"{count} withdrawal events observed for {prefix} in the current ingest window.",
+                evidence={"withdrawal_count": count},
+            )
+            )
+
+    if not pending_anomalies:
+        return 0
+
+    existing_result = await db.execute(
+        select(BGPAnomaly.entity_key).where(
+            BGPAnomaly.entity_key.in_([item.entity_key for item in pending_anomalies])
+        )
+    )
+    existing_keys = {row[0] for row in existing_result.fetchall()}
+
+    created = 0
+    for anomaly in pending_anomalies:
+        if anomaly.entity_key in existing_keys:
+            continue
+        db.add(anomaly)
+        created += 1
+
+    if created:
+        await db.commit()
+    return created

backend/app/services/collectors/bgpstream.py

@@ -0,0 +1,120 @@
+"""BGPStream backfill collector."""
+
+from __future__ import annotations
+
+import asyncio
+import json
+import time
+import urllib.parse
+import urllib.request
+from typing import Any
+
+from app.services.collectors.base import BaseCollector
+from app.services.collectors.bgp_common import create_bgp_anomalies_for_batch, normalize_bgp_event
+
+
+class BGPStreamBackfillCollector(BaseCollector):
+    name = "bgpstream_bgp"
+    priority = "P1"
+    module = "L3"
+    frequency_hours = 6
+    data_type = "bgp_rib"
+    fail_on_empty = True
+
+    async def fetch(self) -> list[dict[str, Any]]:
+        if not self._resolved_url:
+            raise RuntimeError("BGPStream URL is not configured")
+
+        return await asyncio.to_thread(self._fetch_resource_windows)
+
+    def _fetch_resource_windows(self) -> list[dict[str, Any]]:
+        end = int(time.time()) - 3600
+        start = end - 86400
+        params = [
+            ("projects[]", "routeviews"),
+            ("collectors[]", "route-views2"),
+            ("types[]", "updates"),
+            ("intervals[]", f"{start},{end}"),
+        ]
+        url = f"{self._resolved_url}/data?{urllib.parse.urlencode(params)}"
+        request = urllib.request.Request(
+            url,
+            headers={"User-Agent": "Planet-Intelligence-System/1.0 (Python/collector)"},
+        )
+        with urllib.request.urlopen(request, timeout=30) as response:
+            body = json.loads(response.read().decode())
+
+        if body.get("error"):
+            raise RuntimeError(f"BGPStream broker error: {body['error']}")
+
+        return body.get("data", {}).get("resources", [])
+
+    def transform(self, raw_data: list[dict[str, Any]]) -> list[dict[str, Any]]:
+        transformed: list[dict[str, Any]] = []
+        for item in raw_data:
+            if not isinstance(item, dict):
+                continue
+
+            is_broker_window = any(key in item for key in ("filename", "url", "startTime", "start_time"))
+
+            if {"collector", "prefix"} <= set(item.keys()) and not is_broker_window:
+                transformed.append(normalize_bgp_event(item, project="bgpstream"))
+                continue
+
+            # Broker responses provide file windows rather than decoded events.
+            collector = item.get("collector") or item.get("project") or "bgpstream"
+            timestamp = item.get("time") or item.get("startTime") or item.get("start_time")
+            name = item.get("filename") or item.get("url") or f"{collector}-window"
+            normalized = normalize_bgp_event(
+                {
+                    "collector": collector,
+                    "event_type": "rib",
+                    "prefix": item.get("prefix") or "historical-window",
+                    "timestamp": timestamp,
+                    "origin_asn": item.get("origin_asn"),
+                    "path": item.get("path") or [],
+                    "raw_message": item,
+                },
+                project="bgpstream",
+            )
+            transformed.append(
+                normalized
+                | {
+                    "name": name,
+                    "title": f"BGPStream {collector}",
+                    "description": "Historical BGPStream backfill window",
+                    "metadata": {
+                        **normalized["metadata"],
+                        "broker_record": item,
+                    },
+                }
+            )
+        self._latest_transformed_batch = transformed
+        return transformed
+
+    async def run(self, db):
+        result = await super().run(db)
+        if result.get("status") != "success":
+            return result
+
+        snapshot_id = await self._resolve_snapshot_id(db, result.get("task_id"))
+        anomaly_count = await create_bgp_anomalies_for_batch(
+            db,
+            source=self.name,
+            snapshot_id=snapshot_id,
+            task_id=result.get("task_id"),
+            events=getattr(self, "_latest_transformed_batch", []),
+        )
+        result["anomalies_created"] = anomaly_count
+        return result
+
+    async def _resolve_snapshot_id(self, db, task_id: int | None) -> int | None:
+        if task_id is None:
+            return None
+        from sqlalchemy import select
+        from app.models.data_snapshot import DataSnapshot
+
+        result = await db.execute(
+            select(DataSnapshot.id).where(DataSnapshot.task_id == task_id).order_by(DataSnapshot.id.desc())
+        )
+        return result.scalar_one_or_none()

backend/app/services/collectors/celestrak.py

@@ -0,0 +1,115 @@
+"""CelesTrak TLE Collector
+
+Collects satellite TLE (Two-Line Element) data from CelesTrak.org.
+Free, no authentication required.
+"""
+
+import json
+from typing import Dict, Any, List
+import httpx
+
+from app.core.satellite_tle import build_tle_lines_from_elements
+from app.services.collectors.base import BaseCollector
+
+
+class CelesTrakTLECollector(BaseCollector):
+    name = "celestrak_tle"
+    priority = "P2"
+    module = "L3"
+    frequency_hours = 24
+    data_type = "satellite_tle"
+
+    @property
+    def base_url(self) -> str:
+        return "https://celestrak.org/NORAD/elements/gp.php"
+
+    async def fetch(self) -> List[Dict[str, Any]]:
+        satellite_groups = [
+            "starlink",
+            "gps-ops",
+            "galileo",
+            "glonass",
+            "beidou",
+            "leo",
+            "geo",
+            "iridium-next",
+        ]
+
+        all_satellites = []
+
+        async with httpx.AsyncClient(timeout=120.0) as client:
+            for group in satellite_groups:
+                try:
+                    url = f"https://celestrak.org/NORAD/elements/gp.php?GROUP={group}&FORMAT=json"
+                    response = await client.get(url)
+
+                    if response.status_code == 200:
+                        data = response.json()
+                        if isinstance(data, list):
+                            all_satellites.extend(data)
+                            print(f"CelesTrak: Fetched {len(data)} satellites from group '{group}'")
+                except Exception as e:
+                    print(f"CelesTrak: Error fetching group '{group}': {e}")
+
+        if not all_satellites:
+            return self._get_sample_data()
+
+        print(f"CelesTrak: Total satellites fetched: {len(all_satellites)}")
+
+        # Return raw data - base.run() will call transform()
+        return all_satellites
+
+    def transform(self, raw_data: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+        transformed = []
+        for item in raw_data:
+            tle_line1, tle_line2 = build_tle_lines_from_elements(
+                norad_cat_id=item.get("NORAD_CAT_ID"),
+                epoch=item.get("EPOCH"),
+                inclination=item.get("INCLINATION"),
+                raan=item.get("RA_OF_ASC_NODE"),
+                eccentricity=item.get("ECCENTRICITY"),
+                arg_of_perigee=item.get("ARG_OF_PERICENTER"),
+                mean_anomaly=item.get("MEAN_ANOMALY"),
+                mean_motion=item.get("MEAN_MOTION"),
+            )
+
+            transformed.append(
+                {
+                    "name": item.get("OBJECT_NAME", "Unknown"),
+                    "reference_date": item.get("EPOCH", ""),
+                    "metadata": {
+                        "norad_cat_id": item.get("NORAD_CAT_ID"),
+                        "international_designator": item.get("OBJECT_ID"),
+                        "epoch": item.get("EPOCH"),
+                        "mean_motion": item.get("MEAN_MOTION"),
+                        "eccentricity": item.get("ECCENTRICITY"),
+                        "inclination": item.get("INCLINATION"),
+                        "raan": item.get("RA_OF_ASC_NODE"),
+                        "arg_of_perigee": item.get("ARG_OF_PERICENTER"),
+                        "mean_anomaly": item.get("MEAN_ANOMALY"),
+                        "classification_type": item.get("CLASSIFICATION_TYPE"),
+                        "bstar": item.get("BSTAR"),
+                        "mean_motion_dot": item.get("MEAN_MOTION_DOT"),
+                        "mean_motion_ddot": item.get("MEAN_MOTION_DDOT"),
+                        "ephemeris_type": item.get("EPHEMERIS_TYPE"),
+                        # Prefer the original TLE lines when the source provides them.
+                        # If they are missing, store a normalized TLE pair built once on the backend.
+                        "tle_line1": item.get("TLE_LINE1") or tle_line1,
+                        "tle_line2": item.get("TLE_LINE2") or tle_line2,
+                    },
+                }
+            )
+        return transformed
+
+    def _get_sample_data(self) -> List[Dict[str, Any]]:
+        return [
+            {
+                "name": "STARLINK-1000",
+                "norad_cat_id": 44720,
+                "international_designator": "2019-029AZ",
+                "epoch": "2026-03-13T00:00:00Z",
+                "mean_motion": 15.79234567,
+                "eccentricity": 0.0001234,
+                "inclination": 53.0,
+            },
+        ]

backend/app/services/collectors/cloudflare.py

@@ -10,11 +10,12 @@ Some endpoints require authentication for higher rate limits.
 import asyncio
 import os
 from typing import Dict, Any, List
-from datetime import datetime
+from datetime import UTC, datetime
 
 import httpx
 from app.services.collectors.base import HTTPCollector
 
+
 # Cloudflare API token (optional - for higher rate limits)
 CLOUDFLARE_API_TOKEN = os.environ.get("CLOUDFLARE_API_TOKEN", "")
 
@@ -58,7 +59,7 @@ class CloudflareRadarDeviceCollector(HTTPCollector):
                     "other_percent": float(summary.get("other", 0)),
                     "date_range": result.get("meta", {}).get("dateRange", {}),
                 },
-                "reference_date": datetime.utcnow().isoformat(),
+                "reference_date": datetime.now(UTC).isoformat(),
             }
             data.append(entry)
         except (ValueError, TypeError, KeyError):
@@ -106,7 +107,7 @@ class CloudflareRadarTrafficCollector(HTTPCollector):
                         "requests": item.get("requests"),
                         "visit_duration": item.get("visitDuration"),
                     },
-                    "reference_date": item.get("datetime", datetime.utcnow().isoformat()),
+                    "reference_date": item.get("datetime", datetime.now(UTC).isoformat()),
                 }
                 data.append(entry)
             except (ValueError, TypeError, KeyError):
@@ -154,7 +155,7 @@ class CloudflareRadarTopASCollector(HTTPCollector):
                         "traffic_share": item.get("trafficShare"),
                         "country_code": item.get("location", {}).get("countryCode"),
                     },
-                    "reference_date": datetime.utcnow().isoformat(),
+                    "reference_date": datetime.now(UTC).isoformat(),
                 }
                 data.append(entry)
             except (ValueError, TypeError, KeyError):

backend/app/services/collectors/epoch_ai.py

@@ -6,13 +6,14 @@ https://epoch.ai/data/gpu-clusters
 
 import re
 from typing import Dict, Any, List
-from datetime import datetime
+from datetime import UTC, datetime
 from bs4 import BeautifulSoup
 import httpx
 
 from app.services.collectors.base import BaseCollector
 
 
+
 class EpochAIGPUCollector(BaseCollector):
     name = "epoch_ai_gpu"
     priority = "P0"
@@ -63,7 +64,7 @@ class EpochAIGPUCollector(BaseCollector):
                             "metadata": {
                                 "raw_data": perf_cell,
                             },
-                            "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                            "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
                         }
                         data.append(entry)
                     except (ValueError, IndexError, AttributeError):
@@ -113,6 +114,6 @@ class EpochAIGPUCollector(BaseCollector):
                 "metadata": {
                     "note": "Sample data - Epoch AI page structure may vary",
                 },
-                "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
             },
         ]

backend/app/services/collectors/fao_landing.py

@@ -4,12 +4,13 @@ Collects landing point data from FAO CSV API.
 """
 
 from typing import Dict, Any, List
-from datetime import datetime
+from datetime import UTC, datetime
 import httpx
 
 from app.services.collectors.base import BaseCollector
 
 
+
 class FAOLandingPointCollector(BaseCollector):
     name = "fao_landing_points"
     priority = "P1"
@@ -57,7 +58,7 @@ class FAOLandingPointCollector(BaseCollector):
                             "is_tbd": is_tbd,
                             "original_id": feature_id,
                         },
-                        "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                        "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
                     }
                     result.append(entry)
                 except (ValueError, IndexError):

backend/app/services/collectors/huggingface.py

@@ -7,11 +7,12 @@ https://huggingface.co/spaces
 """
 
 from typing import Dict, Any, List
-from datetime import datetime
+from datetime import UTC, datetime
 
 from app.services.collectors.base import HTTPCollector
 
 
+
 class HuggingFaceModelCollector(HTTPCollector):
     name = "huggingface_models"
     priority = "P1"
@@ -45,7 +46,7 @@ class HuggingFaceModelCollector(HTTPCollector):
                         "library_name": item.get("library_name"),
                         "created_at": item.get("createdAt"),
                     },
-                    "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                    "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
                 }
                 data.append(entry)
             except (ValueError, TypeError, KeyError):
@@ -86,7 +87,7 @@ class HuggingFaceDatasetCollector(HTTPCollector):
                         "tags": (item.get("tags", []) or [])[:10],
                         "created_at": item.get("createdAt"),
                     },
-                    "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                    "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
                 }
                 data.append(entry)
             except (ValueError, TypeError, KeyError):
@@ -127,7 +128,7 @@ class HuggingFaceSpacesCollector(HTTPCollector):
                         "tags": (item.get("tags", []) or [])[:10],
                         "created_at": item.get("createdAt"),
                     },
-                    "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                    "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
                 }
                 data.append(entry)
             except (ValueError, TypeError, KeyError):

backend/app/services/collectors/peeringdb.py

@@ -13,11 +13,12 @@ To get higher limits, set PEERINGDB_API_KEY environment variable.
 import asyncio
 import os
 from typing import Dict, Any, List
-from datetime import datetime
+from datetime import UTC, datetime
 
 import httpx
 from app.services.collectors.base import HTTPCollector
 
+
 # PeeringDB API key - read from environment variable
 PEERINGDB_API_KEY = os.environ.get("PEERINGDB_API_KEY", "")
 
@@ -75,7 +76,7 @@ class PeeringDBIXPCollector(HTTPCollector):
         print(f"Warning: PeeringDB collection failed after {max_retries} retries: {last_error}")
         return {}
 
-    async def collect(self) -> List[Dict[str, Any]]:
+    async def fetch(self) -> List[Dict[str, Any]]:
         """Collect IXP data from PeeringDB with rate limit handling"""
         response_data = await self.fetch_with_retry()
         if not response_data:
@@ -105,7 +106,7 @@ class PeeringDBIXPCollector(HTTPCollector):
                         "created": item.get("created"),
                         "updated": item.get("updated"),
                     },
-                    "reference_date": datetime.utcnow().isoformat(),
+                    "reference_date": datetime.now(UTC).isoformat(),
                 }
                 data.append(entry)
             except (ValueError, TypeError, KeyError):
@@ -176,7 +177,7 @@ class PeeringDBNetworkCollector(HTTPCollector):
         print(f"Warning: PeeringDB collection failed after {max_retries} retries: {last_error}")
         return {}
 
-    async def collect(self) -> List[Dict[str, Any]]:
+    async def fetch(self) -> List[Dict[str, Any]]:
         """Collect Network data from PeeringDB with rate limit handling"""
         response_data = await self.fetch_with_retry()
         if not response_data:
@@ -208,7 +209,7 @@ class PeeringDBNetworkCollector(HTTPCollector):
                         "created": item.get("created"),
                         "updated": item.get("updated"),
                     },
-                    "reference_date": datetime.utcnow().isoformat(),
+                    "reference_date": datetime.now(UTC).isoformat(),
                 }
                 data.append(entry)
             except (ValueError, TypeError, KeyError):
@@ -279,7 +280,7 @@ class PeeringDBFacilityCollector(HTTPCollector):
         print(f"Warning: PeeringDB collection failed after {max_retries} retries: {last_error}")
         return {}
 
-    async def collect(self) -> List[Dict[str, Any]]:
+    async def fetch(self) -> List[Dict[str, Any]]:
         """Collect Facility data from PeeringDB with rate limit handling"""
         response_data = await self.fetch_with_retry()
         if not response_data:
@@ -310,7 +311,7 @@ class PeeringDBFacilityCollector(HTTPCollector):
                         "created": item.get("created"),
                         "updated": item.get("updated"),
                     },
-                    "reference_date": datetime.utcnow().isoformat(),
+                    "reference_date": datetime.now(UTC).isoformat(),
                 }
                 data.append(entry)
             except (ValueError, TypeError, KeyError):

backend/app/services/collectors/ris_live.py

@@ -0,0 +1,131 @@
+"""RIPE RIS Live collector."""
+
+from __future__ import annotations
+
+import asyncio
+import json
+import urllib.request
+from typing import Any
+
+from app.services.collectors.base import BaseCollector
+from app.services.collectors.bgp_common import create_bgp_anomalies_for_batch, normalize_bgp_event
+
+
+class RISLiveCollector(BaseCollector):
+    name = "ris_live_bgp"
+    priority = "P1"
+    module = "L3"
+    frequency_hours = 1
+    data_type = "bgp_update"
+    fail_on_empty = True
+    max_messages = 100
+    idle_timeout_seconds = 15
+
+    async def fetch(self) -> list[dict[str, Any]]:
+        if not self._resolved_url:
+            raise RuntimeError("RIS Live URL is not configured")
+
+        return await asyncio.to_thread(self._fetch_via_stream)
+
+    def _fetch_via_stream(self) -> list[dict[str, Any]]:
+        events: list[dict[str, Any]] = []
+        stream_url = "https://ris-live.ripe.net/v1/stream/?format=json&client=planet-ris-live"
+        subscribe = json.dumps(
+            {
+                "host": "rrc00",
+                "type": "UPDATE",
+                "require": "announcements",
+            }
+        )
+        request = urllib.request.Request(
+            stream_url,
+            headers={"X-RIS-Subscribe": subscribe},
+        )
+        with urllib.request.urlopen(request, timeout=20) as response:
+            while len(events) < self.max_messages:
+                line = response.readline().decode().strip()
+                if not line:
+                    break
+                payload = json.loads(line)
+                if payload.get("type") != "ris_message":
+                    continue
+                data = payload.get("data", {})
+                if isinstance(data, dict):
+                    events.append(data)
+        return events
+
+    def transform(self, raw_data: list[dict[str, Any]]) -> list[dict[str, Any]]:
+        transformed: list[dict[str, Any]] = []
+        for item in raw_data:
+            announcements = item.get("announcements") or []
+            withdrawals = item.get("withdrawals") or []
+
+            for announcement in announcements:
+                next_hop = announcement.get("next_hop")
+                for prefix in announcement.get("prefixes") or []:
+                    transformed.append(
+                        normalize_bgp_event(
+                            {
+                                **item,
+                                "collector": item.get("host", "").replace(".ripe.net", ""),
+                                "event_type": "announcement",
+                                "prefix": prefix,
+                                "next_hop": next_hop,
+                            },
+                            project="ris-live",
+                        )
+                    )
+
+            for prefix in withdrawals:
+                transformed.append(
+                    normalize_bgp_event(
+                        {
+                            **item,
+                            "collector": item.get("host", "").replace(".ripe.net", ""),
+                            "event_type": "withdrawal",
+                            "prefix": prefix,
+                        },
+                        project="ris-live",
+                    )
+                )
+
+            if not announcements and not withdrawals:
+                transformed.append(
+                    normalize_bgp_event(
+                        {
+                            **item,
+                            "collector": item.get("host", "").replace(".ripe.net", ""),
+                        },
+                        project="ris-live",
+                    )
+                )
+
+        self._latest_transformed_batch = transformed
+        return transformed
+
+    async def run(self, db):
+        result = await super().run(db)
+        if result.get("status") != "success":
+            return result
+
+        snapshot_id = await self._resolve_snapshot_id(db, result.get("task_id"))
+        anomaly_count = await create_bgp_anomalies_for_batch(
+            db,
+            source=self.name,
+            snapshot_id=snapshot_id,
+            task_id=result.get("task_id"),
+            events=getattr(self, "_latest_transformed_batch", []),
+        )
+        result["anomalies_created"] = anomaly_count
+        return result
+
+    async def _resolve_snapshot_id(self, db, task_id: int | None) -> int | None:
+        if task_id is None:
+            return None
+        from sqlalchemy import select
+        from app.models.data_snapshot import DataSnapshot
+
+        result = await db.execute(
+            select(DataSnapshot.id).where(DataSnapshot.task_id == task_id).order_by(DataSnapshot.id.desc())
+        )
+        return result.scalar_one_or_none()

backend/app/services/collectors/spacetrack.py

@@ -0,0 +1,239 @@
+"""Space-Track TLE Collector
+
+Collects satellite TLE (Two-Line Element) data from Space-Track.org.
+API documentation: https://www.space-track.org/documentation
+"""
+
+import json
+from typing import Dict, Any, List
+import httpx
+
+from app.services.collectors.base import BaseCollector
+from app.core.data_sources import get_data_sources_config
+from app.core.satellite_tle import build_tle_lines_from_elements
+
+
+class SpaceTrackTLECollector(BaseCollector):
+    name = "spacetrack_tle"
+    priority = "P2"
+    module = "L3"
+    frequency_hours = 24
+    data_type = "satellite_tle"
+
+    @property
+    def base_url(self) -> str:
+        config = get_data_sources_config()
+        if self._resolved_url:
+            return self._resolved_url
+        return config.get_yaml_url("spacetrack_tle")
+
+    async def fetch(self) -> List[Dict[str, Any]]:
+        from app.core.config import settings
+
+        username = settings.SPACETRACK_USERNAME
+        password = settings.SPACETRACK_PASSWORD
+
+        if not username or not password:
+            print("SPACETRACK: No credentials configured, using sample data")
+            return self._get_sample_data()
+
+        print(f"SPACETRACK: Attempting to fetch TLE data with username: {username}")
+
+        try:
+            async with httpx.AsyncClient(
+                timeout=120.0,
+                follow_redirects=True,
+                headers={
+                    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+                    "Accept": "application/json, text/html, */*",
+                    "Accept-Language": "en-US,en;q=0.9",
+                    "Referer": "https://www.space-track.org/",
+                },
+            ) as client:
+                await client.get("https://www.space-track.org/")
+
+                login_response = await client.post(
+                    "https://www.space-track.org/ajaxauth/login",
+                    data={
+                        "identity": username,
+                        "password": password,
+                    },
+                )
+                print(f"SPACETRACK: Login response status: {login_response.status_code}")
+                print(f"SPACETRACK: Login response URL: {login_response.url}")
+
+                if login_response.status_code == 403:
+                    print("SPACETRACK: Trying alternate login method...")
+
+                    async with httpx.AsyncClient(
+                        timeout=120.0,
+                        follow_redirects=True,
+                    ) as alt_client:
+                        await alt_client.get("https://www.space-track.org/")
+
+                        form_data = {
+                            "username": username,
+                            "password": password,
+                            "query": "class/gp/NORAD_CAT_ID/25544/format/json",
+                        }
+                        alt_login = await alt_client.post(
+                            "https://www.space-track.org/ajaxauth/login",
+                            data={
+                                "identity": username,
+                                "password": password,
+                            },
+                        )
+                        print(f"SPACETRACK: Alt login status: {alt_login.status_code}")
+
+                        if alt_login.status_code == 200:
+                            tle_response = await alt_client.get(
+                                "https://www.space-track.org/basicspacedata/query/class/gp/NORAD_CAT_ID/25544/format/json"
+                            )
+                            if tle_response.status_code == 200:
+                                data = tle_response.json()
+                                print(f"SPACETRACK: Received {len(data)} records via alt method")
+                                return data
+
+                if login_response.status_code != 200:
+                    print(f"SPACETRACK: Login failed, using sample data")
+                    return self._get_sample_data()
+
+                tle_response = await client.get(
+                    "https://www.space-track.org/basicspacedata/query/class/gp/NORAD_CAT_ID/25544/format/json"
+                )
+                print(f"SPACETRACK: TLE query status: {tle_response.status_code}")
+
+                if tle_response.status_code != 200:
+                    print(f"SPACETRACK: Query failed, using sample data")
+                    return self._get_sample_data()
+
+                data = tle_response.json()
+                print(f"SPACETRACK: Received {len(data)} records")
+                return data
+        except Exception as e:
+            print(f"SPACETRACK: Error - {e}, using sample data")
+            return self._get_sample_data()
+
+        print(f"SPACETRACK: Attempting to fetch TLE data with username: {username}")
+
+        try:
+            async with httpx.AsyncClient(
+                timeout=120.0,
+                follow_redirects=True,
+                headers={
+                    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
+                    "Accept": "application/json, text/html, */*",
+                    "Accept-Language": "en-US,en;q=0.9",
+                },
+            ) as client:
+                # First, visit the main page to get any cookies
+                await client.get("https://www.space-track.org/")
+
+                # Login to get session cookie
+                login_response = await client.post(
+                    "https://www.space-track.org/ajaxauth/login",
+                    data={
+                        "identity": username,
+                        "password": password,
+                    },
+                )
+                print(f"SPACETRACK: Login response status: {login_response.status_code}")
+                print(f"SPACETRACK: Login response URL: {login_response.url}")
+                print(f"SPACETRACK: Login response body: {login_response.text[:500]}")
+
+                if login_response.status_code != 200:
+                    print(f"SPACETRACK: Login failed, using sample data")
+                    return self._get_sample_data()
+
+                # Query for TLE data (get first 1000 satellites)
+                tle_response = await client.get(
+                    "https://www.space-track.org/basicspacedata/query"
+                    "/class/gp"
+                    "/orderby/EPOCH%20desc"
+                    "/limit/1000"
+                    "/format/json"
+                )
+                print(f"SPACETRACK: TLE query status: {tle_response.status_code}")
+
+                if tle_response.status_code != 200:
+                    print(f"SPACETRACK: Query failed, using sample data")
+                    return self._get_sample_data()
+
+                data = tle_response.json()
+                print(f"SPACETRACK: Received {len(data)} records")
+                return data
+        except Exception as e:
+            print(f"SPACETRACK: Error - {e}, using sample data")
+            return self._get_sample_data()
+
+    def transform(self, raw_data: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+        """Transform TLE data to internal format"""
+        transformed = []
+        for item in raw_data:
+            tle_line1, tle_line2 = build_tle_lines_from_elements(
+                norad_cat_id=item.get("NORAD_CAT_ID"),
+                epoch=item.get("EPOCH"),
+                inclination=item.get("INCLINATION"),
+                raan=item.get("RAAN"),
+                eccentricity=item.get("ECCENTRICITY"),
+                arg_of_perigee=item.get("ARG_OF_PERIGEE"),
+                mean_anomaly=item.get("MEAN_ANOMALY"),
+                mean_motion=item.get("MEAN_MOTION"),
+            )
+            transformed.append(
+                {
+                    "name": item.get("OBJECT_NAME", "Unknown"),
+                    "reference_date": item.get("EPOCH", ""),
+                    "metadata": {
+                        "norad_cat_id": item.get("NORAD_CAT_ID"),
+                        "international_designator": item.get("INTL_DESIGNATOR"),
+                        "epoch": item.get("EPOCH"),
+                        "mean_motion": item.get("MEAN_MOTION"),
+                        "eccentricity": item.get("ECCENTRICITY"),
+                        "inclination": item.get("INCLINATION"),
+                        "raan": item.get("RAAN"),
+                        "arg_of_perigee": item.get("ARG_OF_PERIGEE"),
+                        "mean_anomaly": item.get("MEAN_ANOMALY"),
+                        "ephemeris_type": item.get("EPHEMERIS_TYPE"),
+                        "classification_type": item.get("CLASSIFICATION_TYPE"),
+                        "element_set_no": item.get("ELEMENT_SET_NO"),
+                        "rev_at_epoch": item.get("REV_AT_EPOCH"),
+                        "bstar": item.get("BSTAR"),
+                        "mean_motion_dot": item.get("MEAN_MOTION_DOT"),
+                        "mean_motion_ddot": item.get("MEAN_MOTION_DDOT"),
+                        # Prefer original lines from the source, but keep a backend-built pair as a stable fallback.
+                        "tle_line1": item.get("TLE_LINE1") or item.get("TLE1") or tle_line1,
+                        "tle_line2": item.get("TLE_LINE2") or item.get("TLE2") or tle_line2,
+                    },
+                }
+            )
+        return transformed
+
+    def _get_sample_data(self) -> List[Dict[str, Any]]:
+        """Return sample TLE data for testing"""
+        return [
+            {
+                "name": "ISS (ZARYA)",
+                "norad_cat_id": 25544,
+                "international_designator": "1998-067A",
+                "epoch": "2026-03-13T00:00:00Z",
+                "mean_motion": 15.49872723,
+                "eccentricity": 0.0006292,
+                "inclination": 51.6400,
+                "raan": 315.0000,
+                "arg_of_perigee": 100.0000,
+                "mean_anomaly": 260.0000,
+            },
+            {
+                "name": "STARLINK-1000",
+                "norad_cat_id": 44720,
+                "international_designator": "2019-029AZ",
+                "epoch": "2026-03-13T00:00:00Z",
+                "mean_motion": 15.79234567,
+                "eccentricity": 0.0001234,
+                "inclination": 53.0000,
+                "raan": 120.0000,
+                "arg_of_perigee": 90.0000,
+                "mean_anomaly": 270.0000,
+            },
+        ]

backend/app/services/collectors/telegeography.py

@@ -7,13 +7,14 @@ Uses Wayback Machine as backup data source since live data requires JavaScript r
 import json
 import re
 from typing import Dict, Any, List
-from datetime import datetime
+from datetime import UTC, datetime
 from bs4 import BeautifulSoup
 import httpx
 
 from app.services.collectors.base import BaseCollector
 
 
+
 class TeleGeographyCableCollector(BaseCollector):
     name = "telegeography_cables"
     priority = "P1"
@@ -102,7 +103,7 @@ class TeleGeographyCableCollector(BaseCollector):
                         "capacity_tbps": item.get("capacity"),
                         "url": item.get("url"),
                     },
-                    "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                    "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
                 }
                 result.append(entry)
             except (ValueError, TypeError, KeyError):
@@ -130,7 +131,7 @@ class TeleGeographyCableCollector(BaseCollector):
                     "owner": "Meta, Orange, Vodafone, etc.",
                     "status": "active",
                 },
-                "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
             },
             {
                 "source_id": "telegeo_sample_2",
@@ -146,7 +147,7 @@ class TeleGeographyCableCollector(BaseCollector):
                     "owner": "Alibaba, NEC",
                     "status": "planned",
                 },
-                "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
             },
         ]
 
@@ -186,7 +187,7 @@ class TeleGeographyLandingPointCollector(BaseCollector):
                         "cable_count": len(item.get("cables", [])),
                         "url": item.get("url"),
                     },
-                    "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                    "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
                 }
                 result.append(entry)
             except (ValueError, TypeError, KeyError):
@@ -210,7 +211,7 @@ class TeleGeographyLandingPointCollector(BaseCollector):
                 "value": "",
                 "unit": "",
                 "metadata": {"note": "Sample data"},
-                "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
             },
         ]
 
@@ -257,7 +258,7 @@ class TeleGeographyCableSystemCollector(BaseCollector):
                         "investment": item.get("investment"),
                         "url": item.get("url"),
                     },
-                    "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                    "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
                 }
                 result.append(entry)
             except (ValueError, TypeError, KeyError):
@@ -281,6 +282,6 @@ class TeleGeographyCableSystemCollector(BaseCollector):
                 "value": "5000",
                 "unit": "km",
                 "metadata": {"note": "Sample data"},
-                "reference_date": datetime.utcnow().strftime("%Y-%m-%d"),
+                "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
             },
         ]

backend/app/services/collectors/top500.py

@@ -4,9 +4,9 @@ Collects data from TOP500 supercomputer rankings.
 https://top500.org/lists/top500/
 """
 
+import asyncio
 import re
 from typing import Dict, Any, List
-from datetime import datetime
 from bs4 import BeautifulSoup
 import httpx
 
@@ -21,14 +21,108 @@ class TOP500Collector(BaseCollector):
     data_type = "supercomputer"
 
     async def fetch(self) -> List[Dict[str, Any]]:
-        """Fetch TOP500 data from website (scraping)"""
+        """Fetch TOP500 list data and enrich each row with detail-page metadata."""
-        # Get the latest list page
         url = "https://top500.org/lists/top500/list/2025/11/"
 
-        async with httpx.AsyncClient(timeout=60.0) as client:
+        async with httpx.AsyncClient(timeout=60.0, follow_redirects=True) as client:
             response = await client.get(url)
             response.raise_for_status()
-            return self.parse_response(response.text)
+            entries = self.parse_response(response.text)
+
+            semaphore = asyncio.Semaphore(8)
+
+            async def enrich(entry: Dict[str, Any]) -> Dict[str, Any]:
+                detail_url = entry.pop("_detail_url", "")
+                if not detail_url:
+                    return entry
+
+                async with semaphore:
+                    try:
+                        detail_response = await client.get(detail_url)
+                        detail_response.raise_for_status()
+                        entry["metadata"].update(self.parse_detail_response(detail_response.text))
+                    except Exception:
+                        entry["metadata"]["detail_fetch_failed"] = True
+                return entry
+
+            return await asyncio.gather(*(enrich(entry) for entry in entries))
+
+    def _extract_system_fields(self, system_cell) -> Dict[str, str]:
+        link = system_cell.find("a")
+        system_name = link.get_text(" ", strip=True) if link else system_cell.get_text(" ", strip=True)
+        detail_url = ""
+        if link and link.get("href"):
+            detail_url = f"https://top500.org{link.get('href')}"
+
+        manufacturer = ""
+        if link and link.next_sibling:
+            manufacturer = str(link.next_sibling).strip(" ,\n\t")
+
+        cell_text = system_cell.get_text("\n", strip=True)
+        lines = [line.strip(" ,") for line in cell_text.splitlines() if line.strip()]
+
+        site = ""
+        country = ""
+        if lines:
+            system_name = lines[0]
+        if len(lines) >= 3:
+            site = lines[-2]
+            country = lines[-1]
+        elif len(lines) == 2:
+            country = lines[-1]
+
+        if not manufacturer and len(lines) >= 2:
+            manufacturer = lines[1]
+
+        return {
+            "name": system_name,
+            "manufacturer": manufacturer,
+            "site": site,
+            "country": country,
+            "detail_url": detail_url,
+        }
+
+    def parse_detail_response(self, html: str) -> Dict[str, Any]:
+        soup = BeautifulSoup(html, "html.parser")
+        detail_table = soup.find("table", {"class": "table table-condensed"})
+        if not detail_table:
+            return {}
+
+        detail_map: Dict[str, Any] = {}
+        label_aliases = {
+            "Site": "site",
+            "Manufacturer": "manufacturer",
+            "Cores": "cores",
+            "Processor": "processor",
+            "Interconnect": "interconnect",
+            "Installation Year": "installation_year",
+            "Linpack Performance (Rmax)": "rmax",
+            "Theoretical Peak (Rpeak)": "rpeak",
+            "Nmax": "nmax",
+            "HPCG": "hpcg",
+            "Power": "power",
+            "Power Measurement Level": "power_measurement_level",
+            "Operating System": "operating_system",
+            "Compiler": "compiler",
+            "Math Library": "math_library",
+            "MPI": "mpi",
+        }
+
+        for row in detail_table.find_all("tr"):
+            header = row.find("th")
+            value_cell = row.find("td")
+            if not header or not value_cell:
+                continue
+
+            label = header.get_text(" ", strip=True).rstrip(":")
+            key = label_aliases.get(label)
+            if not key:
+                continue
+
+            value = value_cell.get_text(" ", strip=True)
+            detail_map[key] = value
+
+        return detail_map
 
     def parse_response(self, html: str) -> List[Dict[str, Any]]:
         """Parse TOP500 HTML response"""
@@ -36,27 +130,26 @@ class TOP500Collector(BaseCollector):
         soup = BeautifulSoup(html, "html.parser")
 
         # Find the table with TOP500 data
-        table = soup.find("table", {"class": "top500-table"})
+        table = None
-        if not table:
+        for candidate in soup.find_all("table"):
-            # Try alternative table selector
+            header_cells = [
-            table = soup.find("table", {"id": "top500"})
+                cell.get_text(" ", strip=True) for cell in candidate.select("thead th")
-
+            ]
-        if not table:
+            normalized_headers = [header.lower() for header in header_cells]
-            # Try to find any table with rank data
+            if (
-            tables = soup.find_all("table")
+                "rank" in normalized_headers
-            for t in tables:
+                and "system" in normalized_headers
-                if t.find(string=re.compile(r"Rank.*System.*Cores.*Rmax", re.I)):
+                and any("cores" in header for header in normalized_headers)
-                    table = t
+                and any("rmax" in header for header in normalized_headers)
+            ):
+                table = candidate
                 break
 
         if not table:
-            # Fallback: try to extract data from any table
+            table = soup.find("table", {"class": "top500-table"}) or soup.find("table", {"id": "top500"})
-            tables = soup.find_all("table")
-            if tables:
-                table = tables[0]
 
         if table:
-            rows = table.find_all("tr")
+            rows = table.select("tr")
             for row in rows[1:]:  # Skip header row
                 cells = row.find_all(["td", "th"])
                 if len(cells) >= 6:
@@ -68,43 +161,26 @@ class TOP500Collector(BaseCollector):
 
                         rank = int(rank_text)
 
-                        # System name (may contain link)
                         system_cell = cells[1]
-                        system_name = system_cell.get_text(strip=True)
+                        system_fields = self._extract_system_fields(system_cell)
-                        # Try to get full name from link title or data attribute
+                        system_name = system_fields["name"]
-                        link = system_cell.find("a")
+                        manufacturer = system_fields["manufacturer"]
-                        if link and link.get("title"):
+                        site = system_fields["site"]
-                            system_name = link.get("title")
+                        country = system_fields["country"]
+                        detail_url = system_fields["detail_url"]
 
-                        # Country
-                        country_cell = cells[2]
-                        country = country_cell.get_text(strip=True)
-                        # Try to get country from data attribute or image alt
-                        img = country_cell.find("img")
-                        if img and img.get("alt"):
-                            country = img.get("alt")
-
-                        # Extract location (city)
                         city = ""
-                        location_text = country_cell.get_text(strip=True)
+                        cores = cells[2].get_text(strip=True).replace(",", "")
-                        if "(" in location_text and ")" in location_text:
-                            city = location_text.split("(")[0].strip()
 
-                        # Cores
+                        rmax_text = cells[3].get_text(strip=True)
-                        cores = cells[3].get_text(strip=True).replace(",", "")
-
-                        # Rmax
-                        rmax_text = cells[4].get_text(strip=True)
                         rmax = self._parse_performance(rmax_text)
 
-                        # Rpeak
+                        rpeak_text = cells[4].get_text(strip=True)
-                        rpeak_text = cells[5].get_text(strip=True)
                         rpeak = self._parse_performance(rpeak_text)
 
-                        # Power (optional)
                         power = ""
-                        if len(cells) >= 7:
+                        if len(cells) >= 6:
-                            power = cells[6].get_text(strip=True)
+                            power = cells[5].get_text(strip=True).replace(",", "")
 
                         entry = {
                             "source_id": f"top500_{rank}",
@@ -117,10 +193,14 @@ class TOP500Collector(BaseCollector):
                             "unit": "PFlop/s",
                             "metadata": {
                                 "rank": rank,
-                                "r_peak": rpeak,
-                                "power": power,
                                 "cores": cores,
+                                "rmax": rmax_text,
+                                "rpeak": rpeak_text,
+                                "power": power,
+                                "manufacturer": manufacturer,
+                                "site": site,
                             },
+                            "_detail_url": detail_url,
                             "reference_date": "2025-11-01",
                         }
                         data.append(entry)
@@ -184,10 +264,15 @@ class TOP500Collector(BaseCollector):
                 "unit": "PFlop/s",
                 "metadata": {
                     "rank": 1,
-                    "r_peak": 2746.38,
+                    "cores": "11039616",
-                    "power": 29581,
+                    "rmax": "1742.00",
-                    "cores": 11039616,
+                    "rpeak": "2746.38",
+                    "power": "29581",
                     "manufacturer": "HPE",
+                    "site": "DOE/NNSA/LLNL",
+                    "processor": "AMD 4th Gen EPYC 24C 1.8GHz",
+                    "interconnect": "Slingshot-11",
+                    "installation_year": "2025",
                 },
                 "reference_date": "2025-11-01",
             },
@@ -202,10 +287,12 @@ class TOP500Collector(BaseCollector):
                 "unit": "PFlop/s",
                 "metadata": {
                     "rank": 2,
-                    "r_peak": 2055.72,
+                    "cores": "9066176",
-                    "power": 24607,
+                    "rmax": "1353.00",
-                    "cores": 9066176,
+                    "rpeak": "2055.72",
+                    "power": "24607",
                     "manufacturer": "HPE",
+                    "site": "DOE/SC/Oak Ridge National Laboratory",
                 },
                 "reference_date": "2025-11-01",
             },
@@ -220,9 +307,10 @@ class TOP500Collector(BaseCollector):
                 "unit": "PFlop/s",
                 "metadata": {
                     "rank": 3,
-                    "r_peak": 1980.01,
+                    "cores": "9264128",
-                    "power": 38698,
+                    "rmax": "1012.00",
-                    "cores": 9264128,
+                    "rpeak": "1980.01",
+                    "power": "38698",
                     "manufacturer": "Intel",
                 },
                 "reference_date": "2025-11-01",

backend/app/services/scheduler.py

@@ -1,15 +1,18 @@
-"""Task Scheduler for running collection jobs"""
+"""Task Scheduler for running collection jobs."""
 
 import asyncio
 import logging
-from datetime import datetime
+from datetime import UTC, datetime, timedelta
-from typing import Dict, Any
+from typing import Any, Dict, Optional
 
 from apscheduler.schedulers.asyncio import AsyncIOScheduler
 from apscheduler.triggers.interval import IntervalTrigger
-from sqlalchemy.ext.asyncio import AsyncSession
+from sqlalchemy import select
 
 from app.db.session import async_session_factory
+from app.core.time import to_iso8601_utc
+from app.models.datasource import DataSource
+from app.models.task import CollectionTask
 from app.services.collectors.registry import collector_registry
 
 logger = logging.getLogger(__name__)
@@ -17,132 +20,185 @@ logger = logging.getLogger(__name__)
 scheduler = AsyncIOScheduler()
 
 
-COLLECTOR_TO_ID = {
+async def _update_next_run_at(datasource: DataSource, session) -> None:
-    "top500": 1,
+    job = scheduler.get_job(datasource.source)
-    "epoch_ai_gpu": 2,
+    datasource.next_run_at = job.next_run_time if job else None
-    "huggingface_models": 3,
+    await session.commit()
-    "huggingface_datasets": 4,
+
-    "huggingface_spaces": 5,
+
-    "peeringdb_ixp": 6,
+async def _apply_datasource_schedule(datasource: DataSource, session) -> None:
-    "peeringdb_network": 7,
+    collector = collector_registry.get(datasource.source)
-    "peeringdb_facility": 8,
+    if not collector:
-    "telegeography_cables": 9,
+        logger.warning("Collector not found for datasource %s", datasource.source)
-    "telegeography_landing": 10,
+        return
-    "telegeography_systems": 11,
+
-    "arcgis_cables": 15,
+    collector_registry.set_active(datasource.source, datasource.is_active)
-    "fao_landing_points": 16,
+
-}
+    existing_job = scheduler.get_job(datasource.source)
+    if existing_job:
+        scheduler.remove_job(datasource.source)
+
+    if datasource.is_active:
+        scheduler.add_job(
+            run_collector_task,
+            trigger=IntervalTrigger(minutes=max(1, datasource.frequency_minutes)),
+            id=datasource.source,
+            name=datasource.name,
+            replace_existing=True,
+            kwargs={"collector_name": datasource.source},
+        )
+        logger.info(
+            "Scheduled collector: %s (every %sm)",
+            datasource.source,
+            datasource.frequency_minutes,
+        )
+    else:
+        logger.info("Collector disabled: %s", datasource.source)
+
+    await _update_next_run_at(datasource, session)
 
 
 async def run_collector_task(collector_name: str):
-    """Run a single collector task"""
+    """Run a single collector task."""
     collector = collector_registry.get(collector_name)
     if not collector:
-        logger.error(f"Collector not found: {collector_name}")
+        logger.error("Collector not found: %s", collector_name)
         return
 
-    # Get the correct datasource_id
+    async with async_session_factory() as db:
-    datasource_id = COLLECTOR_TO_ID.get(collector_name, 1)
+        result = await db.execute(select(DataSource).where(DataSource.source == collector_name))
+        datasource = result.scalar_one_or_none()
+        if not datasource:
+            logger.error("Datasource not found for collector: %s", collector_name)
+            return
+
+        if not datasource.is_active:
+            logger.info("Skipping disabled collector: %s", collector_name)
+            return
+
+        try:
+            collector._datasource_id = datasource.id
+            logger.info("Running collector: %s (datasource_id=%s)", collector_name, datasource.id)
+            task_result = await collector.run(db)
+            datasource.last_run_at = datetime.now(UTC)
+            datasource.last_status = task_result.get("status")
+            await _update_next_run_at(datasource, db)
+            logger.info("Collector %s completed: %s", collector_name, task_result)
+        except Exception as exc:
+            datasource.last_run_at = datetime.now(UTC)
+            datasource.last_status = "failed"
+            await db.commit()
+            logger.exception("Collector %s failed: %s", collector_name, exc)
+
+
+async def cleanup_stale_running_tasks(max_age_hours: int = 2) -> int:
+    """Mark stale running tasks as failed after restarts or collector hangs."""
+    cutoff = datetime.now(UTC) - timedelta(hours=max_age_hours)
 
     async with async_session_factory() as db:
-        try:
+        result = await db.execute(
-            # Set the datasource_id on the collector instance
+            select(CollectionTask).where(
-            collector._datasource_id = datasource_id
+                CollectionTask.status == "running",
-
+                CollectionTask.started_at.is_not(None),
-            logger.info(f"Running collector: {collector_name} (datasource_id={datasource_id})")
+                CollectionTask.started_at < cutoff,
-            result = await collector.run(db)
-            logger.info(f"Collector {collector_name} completed: {result}")
-        except Exception as e:
-            logger.error(f"Collector {collector_name} failed: {e}")
-
-
-def start_scheduler():
-    """Start the scheduler with all registered collectors"""
-    collectors = collector_registry.all()
-
-    for name, collector in collectors.items():
-        if collector_registry.is_active(name):
-            scheduler.add_job(
-                run_collector_task,
-                trigger=IntervalTrigger(hours=collector.frequency_hours),
-                id=name,
-                name=name,
-                replace_existing=True,
-                kwargs={"collector_name": name},
             )
-            logger.info(f"Scheduled collector: {name} (every {collector.frequency_hours}h)")
+        )
+        stale_tasks = result.scalars().all()
 
+        for task in stale_tasks:
+            task.status = "failed"
+            task.phase = "failed"
+            task.completed_at = datetime.now(UTC)
+            existing_error = (task.error_message or "").strip()
+            cleanup_error = "Marked failed automatically after stale running task cleanup"
+            task.error_message = f"{existing_error}\n{cleanup_error}".strip() if existing_error else cleanup_error
+
+        if stale_tasks:
+            await db.commit()
+            logger.warning("Cleaned up %s stale running collection task(s)", len(stale_tasks))
+
+        return len(stale_tasks)
+
+
+def start_scheduler() -> None:
+    """Start the scheduler."""
+    if not scheduler.running:
         scheduler.start()
         logger.info("Scheduler started")
 
 
-def stop_scheduler():
+def stop_scheduler() -> None:
-    """Stop the scheduler"""
+    """Stop the scheduler."""
-    scheduler.shutdown()
+    if scheduler.running:
+        scheduler.shutdown(wait=False)
         logger.info("Scheduler stopped")
 
 
+async def sync_scheduler_with_datasources() -> None:
+    """Synchronize scheduler jobs with datasource table."""
+    async with async_session_factory() as db:
+        result = await db.execute(select(DataSource).order_by(DataSource.id))
+        datasources = result.scalars().all()
+
+        configured_sources = {datasource.source for datasource in datasources}
+        for job in list(scheduler.get_jobs()):
+            if job.id not in configured_sources:
+                scheduler.remove_job(job.id)
+
+        for datasource in datasources:
+            await _apply_datasource_schedule(datasource, db)
+
+
+async def sync_datasource_job(datasource_id: int) -> bool:
+    """Synchronize a single datasource job after settings changes."""
+    async with async_session_factory() as db:
+        datasource = await db.get(DataSource, datasource_id)
+        if not datasource:
+            return False
+
+        await _apply_datasource_schedule(datasource, db)
+        return True
+
+
 def get_scheduler_jobs() -> list[Dict[str, Any]]:
-    """Get all scheduled jobs"""
+    """Get all scheduled jobs."""
     jobs = []
     for job in scheduler.get_jobs():
         jobs.append(
             {
                 "id": job.id,
                 "name": job.name,
-                "next_run_time": job.next_run_time.isoformat() if job.next_run_time else None,
+                "next_run_time": to_iso8601_utc(job.next_run_time),
                 "trigger": str(job.trigger),
             }
         )
     return jobs
 
 
-def add_job(collector_name: str, hours: int = 4):
+async def get_latest_task_id_for_datasource(datasource_id: int) -> Optional[int]:
-    """Add a new scheduled job"""
+    from app.models.task import CollectionTask
-    collector = collector_registry.get(collector_name)
-    if not collector:
-        raise ValueError(f"Collector not found: {collector_name}")
 
-    scheduler.add_job(
+    async with async_session_factory() as db:
-        run_collector_task,
+        result = await db.execute(
-        trigger=IntervalTrigger(hours=hours),
+            select(CollectionTask.id)
-        id=collector_name,
+            .where(CollectionTask.datasource_id == datasource_id)
-        name=collector_name,
+            .order_by(CollectionTask.created_at.desc(), CollectionTask.id.desc())
-        replace_existing=True,
+            .limit(1)
-        kwargs={"collector_name": collector_name},
         )
-    logger.info(f"Added scheduled job: {collector_name} (every {hours}h)")
+        return result.scalar_one_or_none()
-
-
-def remove_job(collector_name: str):
-    """Remove a scheduled job"""
-    scheduler.remove_job(collector_name)
-    logger.info(f"Removed scheduled job: {collector_name}")
-
-
-def pause_job(collector_name: str):
-    """Pause a scheduled job"""
-    scheduler.pause_job(collector_name)
-    logger.info(f"Paused job: {collector_name}")
-
-
-def resume_job(collector_name: str):
-    """Resume a scheduled job"""
-    scheduler.resume_job(collector_name)
-    logger.info(f"Resumed job: {collector_name}")
 
 
 def run_collector_now(collector_name: str) -> bool:
-    """Run a collector immediately (not scheduled)"""
+    """Run a collector immediately (not scheduled)."""
     collector = collector_registry.get(collector_name)
     if not collector:
-        logger.error(f"Collector not found: {collector_name}")
+        logger.error("Collector not found: %s", collector_name)
         return False
 
     try:
         asyncio.create_task(run_collector_task(collector_name))
-        logger.info(f"Triggered collector: {collector_name}")
+        logger.info("Triggered collector: %s", collector_name)
         return True
-    except Exception as e:
+    except Exception as exc:
-        logger.error(f"Failed to trigger collector {collector_name}: {e}")
+        logger.error("Failed to trigger collector %s: %s", collector_name, exc)
         return False

backend/requirements.txt

@@ -16,3 +16,4 @@ email-validator
 apscheduler>=3.10.4
 pytest>=7.4.0
 pytest-asyncio>=0.23.0
+networkx>=3.0