release: bump version to 0.66.2

Release 0.58.0 includes the Earth high-precision boundary PMTiles/MVT pipeline, standardized Earth boundary source collectors, China POV boundary configuration templates, and removal of the legacy low-precision GeoJSON fallback. It also adds Earth news target-location queueing/archive support, fixes datasource task status visibility, documents the Earth surface depth-spacing rules that prevent far-zoom z-fighting snow/black blocks, and updates bilingual operations/developer docs.

.claude/commands/docs.md

@@ -46,6 +46,16 @@ rg -n "class |def |function |export |router|@router|interface |type " <path>
 - Keep filenames lowercase and hyphenated.
 - Apply the repository-specific rules file before writing.
 
+#### Document Audience Routing (Planet)
+
+In this repository, classify the action's performer before picking a target file:
+
+- Browser/UI end user → `docs/technical/{zh,en}/manual.md` or `quickstart.md`.
+- Shell / Docker / log paths / `planet.sh` / SMTP fallbacks / port forwarding → `docs/technical/{zh,en}/ops-runbook.md` (or an existing `ops-*.md`).
+- Second-party developers → existing `*-context.md` / `backend-*.md` / `earth-*.md` files.
+
+Never put shell commands, log paths, or Docker operations into `manual.md` / `quickstart.md`. Never put UI button labels or screenshots into `ops-*.md`. When the same action has both a UI and a CLI path, write each in its own home and cross-link them with one sentence.
+
 For ambiguous or large documentation changes, briefly state the intended doc plan before editing. For clear small changes, proceed directly.
 
 ### Step 3 — Write
@@ -63,6 +73,7 @@ Style:
 - Use fenced code blocks with language tags.
 - Prefer tables for comparisons or parameter lists.
 - Keep snippets concise and relevant.
+- For UI labels, chart labels, feature names, datasource names, and other terms that may become mixed Chinese/English copy, check `docs/technical/{zh,en}/naming-glossary.md` and use the documented display name. If a confusing term is missing, update the glossary in both languages as part of the docs change.
 
 ### Step 4 — Verify
 

.codex/skills/docs/SKILL.md

@@ -52,6 +52,7 @@ rg -n "class |def |function |export |router|@router|interface |type " <path>
 - Keep code snippets short and directly relevant.
 - List related files only when they help future maintainers navigate.
 - Use the repository’s existing language, heading style, and naming conventions.
+- For UI labels, chart labels, feature names, datasource names, and other terms that may become mixed Chinese/English copy, check `docs/technical/{zh,en}/naming-glossary.md` and use the documented display name. If a confusing term is missing, update the glossary in both languages as part of the docs change.
 
 4. Verify:
 

.dockerignore

@@ -2,9 +2,14 @@
 
 !pyproject.toml
 !uv.lock
+!VERSION
+!backend/
+!backend/**
 !aiprovider/
 !aiprovider/**
 
+backend/.env
+backend/.env.*
 aiprovider/.env
 aiprovider/.env.*
 !aiprovider/.env.example

.gitea/workflows/ci.yaml

@@ -0,0 +1,64 @@
+name: ci
+
+on:
+  push:
+    branches:
+      - dev
+      - main
+  pull_request:
+
+env:
+  REGISTRY: gitea.rclaw.top
+  IMAGE_NAMESPACE: linkong/planet
+
+jobs:
+  backend:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install uv
+        run: curl -LsSf https://astral.sh/uv/install.sh | sh
+      - name: Sync Python dependencies
+        run: ~/.local/bin/uv sync --group dev
+      - name: Run backend smoke tests
+        working-directory: backend
+        run: PYTHONPATH=. "$GITHUB_WORKSPACE/.venv/bin/python" -m pytest -s tests/test_api.py tests/test_realtime_sources.py -q
+
+  frontend:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install Bun
+        run: curl -fsSL https://bun.sh/install | bash
+      - name: Build frontend
+        working-directory: frontend
+        run: |
+          ~/.bun/bin/bun install --frozen-lockfile
+          ~/.bun/bin/bun run build
+
+  delivery:
+    runs-on: ubuntu-latest
+    needs:
+      - backend
+      - frontend
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install Helm
+        run: |
+          mkdir -p "$HOME/.local/bin"
+          curl -fsSL https://get.helm.sh/helm-v3.15.4-linux-amd64.tar.gz -o /tmp/helm.tar.gz
+          tar -xzf /tmp/helm.tar.gz -C /tmp
+          mv /tmp/linux-amd64/helm "$HOME/.local/bin/helm"
+          echo "$HOME/.local/bin" >> "$GITHUB_PATH"
+      - name: Docker build smoke
+        run: |
+          docker build -t "$REGISTRY/$IMAGE_NAMESPACE/frontend:${GITHUB_SHA}" ./frontend
+          docker build -t "$REGISTRY/$IMAGE_NAMESPACE/backend:${GITHUB_SHA}" -f backend/Dockerfile .
+          docker build -t "$REGISTRY/$IMAGE_NAMESPACE/aiprovider:${GITHUB_SHA}" -f aiprovider/Dockerfile .
+      - name: Helm template smoke
+        run: |
+          helm lint deploy/helm/planet
+          helm template planet-staging deploy/helm/planet \
+            --namespace planet-staging \
+            -f deploy/helm/planet/values.single-node.yaml \
+            --set image.tag="${GITHUB_SHA}" >/tmp/planet-rendered.yaml

.gitea/workflows/deploy-staging.yaml

@@ -0,0 +1,67 @@
+name: deploy-staging
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+
+env:
+  REGISTRY: gitea.rclaw.top
+  IMAGE_NAMESPACE: linkong/planet
+  RELEASE_NAME: planet-staging
+  NAMESPACE: planet-staging
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install deploy tools
+        run: |
+          mkdir -p "$HOME/.local/bin"
+          curl -fsSL https://get.helm.sh/helm-v3.15.4-linux-amd64.tar.gz -o /tmp/helm.tar.gz
+          tar -xzf /tmp/helm.tar.gz -C /tmp
+          mv /tmp/linux-amd64/helm "$HOME/.local/bin/helm"
+          curl -fsSL https://dl.k8s.io/release/v1.30.5/bin/linux/amd64/kubectl -o /tmp/kubectl
+          install -m 0755 /tmp/kubectl "$HOME/.local/bin/kubectl"
+          echo "$HOME/.local/bin" >> "$GITHUB_PATH"
+      - name: Configure kubeconfig
+        run: |
+          mkdir -p "$HOME/.kube"
+          printf "%s" "${{ secrets.KUBE_CONFIG_STAGING }}" | base64 -d > "$HOME/.kube/config"
+          chmod 600 "$HOME/.kube/config"
+      - name: Deploy Helm release
+        run: |
+          kubectl create namespace "$NAMESPACE" --dry-run=client -o yaml | kubectl apply -f -
+          helm upgrade --install "$RELEASE_NAME" deploy/helm/planet \
+            --namespace "$NAMESPACE" \
+            -f deploy/helm/planet/values.single-node.yaml \
+            --set global.imageRegistry="$REGISTRY" \
+            --set global.imageNamespace="$IMAGE_NAMESPACE" \
+            --set image.tag="${GITHUB_SHA}"
+      - name: Wait for rollout
+        run: |
+          kubectl rollout status deployment/planet-frontend -n "$NAMESPACE" --timeout=180s
+          kubectl rollout status deployment/planet-backend -n "$NAMESPACE" --timeout=180s
+          kubectl rollout status deployment/planet-aiprovider -n "$NAMESPACE" --timeout=180s
+      - name: Smoke test services
+        run: |
+          kubectl run planet-smoke-${GITHUB_RUN_NUMBER} \
+            --rm -i --restart=Never \
+            --namespace "$NAMESPACE" \
+            --image=curlimages/curl:8.11.1 \
+            --command -- sh -c '
+              set -eu
+              curl -fsS http://planet-frontend:3000/ >/dev/null
+              curl -fsS http://planet-frontend:3000/health >/dev/null
+              curl -fsS http://planet-frontend:3000/api/health >/dev/null
+              curl -fsS http://planet-backend:8000/health >/dev/null
+              curl -fsS http://planet-aiprovider:8010/health >/dev/null
+            '
+      - name: Collect diagnostics on failure
+        if: failure()
+        run: |
+          kubectl get all -n "$NAMESPACE" -o wide || true
+          kubectl describe pods -n "$NAMESPACE" || true
+          kubectl logs -n "$NAMESPACE" -l app.kubernetes.io/instance="$RELEASE_NAME" --all-containers --tail=200 || true

.gitea/workflows/release.yaml

@@ -0,0 +1,58 @@
+name: release
+
+on:
+  push:
+    branches:
+      - main
+    tags:
+      - "v*"
+  workflow_dispatch:
+
+env:
+  REGISTRY: gitea.rclaw.top
+  IMAGE_NAMESPACE: linkong/planet
+
+jobs:
+  images:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Resolve image tags
+        id: meta
+        run: |
+          echo "sha_tag=${GITHUB_SHA}" >> "$GITHUB_OUTPUT"
+          if printf "%s" "${GITHUB_REF}" | grep -q '^refs/tags/v'; then
+            echo "release_tag=${GITHUB_REF_NAME}" >> "$GITHUB_OUTPUT"
+          else
+            echo "release_tag=" >> "$GITHUB_OUTPUT"
+          fi
+      - name: Login to registry
+        run: echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login "$REGISTRY" -u "${{ secrets.REGISTRY_USER }}" --password-stdin
+      - name: Build and push images
+        run: |
+          for service in frontend backend aiprovider; do
+            case "$service" in
+              frontend)
+                dockerfile="./frontend/Dockerfile"
+                context="./frontend"
+                ;;
+              backend)
+                dockerfile="backend/Dockerfile"
+                context="."
+                ;;
+              aiprovider)
+                dockerfile="aiprovider/Dockerfile"
+                context="."
+                ;;
+            esac
+
+            image="$REGISTRY/$IMAGE_NAMESPACE/$service:${{ steps.meta.outputs.sha_tag }}"
+            docker build -t "$image" -f "$dockerfile" "$context"
+            docker push "$image"
+
+            if [ -n "${{ steps.meta.outputs.release_tag }}" ]; then
+              release_image="$REGISTRY/$IMAGE_NAMESPACE/$service:${{ steps.meta.outputs.release_tag }}"
+              docker tag "$image" "$release_image"
+              docker push "$release_image"
+            fi
+          done

.gitignore

@@ -8,6 +8,7 @@
 .env
 .env.local
 .env.*.local
+config/earth-boundary-sources.local.json
 *.pem
 *.key
 *.crt
@@ -150,3 +151,9 @@ temp/
 # Runtime Data
 # ----------------------
 data/ai/bgp-briefs/
+data/earth-boundary-sources/
+
+# Generated Earth boundary tile artifacts. Keep source configs and builders in
+# Git; publish PMTiles/MVT artifacts through release/deploy storage instead of
+# committing thousands of generated tile files.
+frontend/public/earth/data/boundaries/

README.md

@@ -8,68 +8,54 @@
 
 ## 系统架构
 
+当前仓库的核心形态是“Web Earth 可视化 + React 运维台 + FastAPI 数据与 AI 编排后端 + 独立模型适配层”。物理大屏与 UE 客户端仍是长期方向，但不再作为本地开发和当前发布的必需运行单元。
+
 ```
-┌─────────────────────────────────────────────────────────────────────────┐
-│                           物理大屏展示层                                  │
-│  ┌─────────────────────────────────────────────────────────────────┐    │
-│  │         偏振片3D大屏 (2m×3m, 4K, 120Hz, 眼镜式)                 │    │
-│  │  ┌─────────────────────────────────────────────────────────┐    │    │
-│  │  │              虚幻引擎 UE5 客户端                          │    │    │
-│  │  │  ├── 3D地球渲染 (Cesium for UE)                          │    │    │
-│  │  │  ├── 算力点可视化 (GPU集群、智算中心)                     │    │    │
-│  │  │  ├── 连接弧线 (光缆、路由、数据流向)                      │    │    │
-│  │  │  ├── 粒子效果 (数据流动、告警提示)                        │    │    │
-│  │  │  └── 自动巡航相机 + 交互控制                              │    │    │
-│  │  └─────────────────────────────────────────────────────────┘    │    │
-│  └─────────────────────────────────────────────────────────────────┘    │
-└─────────────────────────────────────────────────────────────────────────┘
-                                    ▲
-                                    │ WebSocket (实时推送)
-                                    │ 120Hz 心跳 / 数据帧同步
-                                    ▼
-┌─────────────────────────────────────────────────────────────────────────┐
-│                           数据中台服务层 (FastAPI)                        │
-│  ┌─────────────────────────────────────────────────────────────────┐    │
-│  │                      API Gateway (Redis 限流)                    │    │
-│  └─────────────────────────────────────────────────────────────────┘    │
-│                                    │                                    │
-│  ┌───────────────────┬──────────────────────────┬──────────────────┐   │
-│  │    数据采集服务    │      核心业务服务         │    运维管理服务   │   │
-│  │  ┌─────────────┐  │  ┌─────────────────┐    │  ┌─────────────┐ │   │
-│  │  │ 调度中心    │  │  │ WebSocket 服务  │    │  │ 用户管理    │ │   │
-│  │  │ (Celery)   │  │  │ (FastAPI)       │    │  │ (JWT Auth)  │ │   │
-│  │  └─────────────┘  │  └─────────────────┘    │  └─────────────┘ │   │
-│  │  ┌─────────────┐  │  ┌─────────────────┐    │  ┌─────────────┐ │   │
-│  │  │ 采集器池    │  │  │ 数据查询 API    │    │  │ 数据源配置  │ │   │
-│  │  │ (10+源)    │  │  │ (REST)          │    │  │ 监控告警    │ │   │
-│  │  └─────────────┘  │  └─────────────────┘    │  └─────────────┘ │   │
-│  │  ┌─────────────┐  │  ┌─────────────────┐    │  ┌─────────────┐ │   │
-│  │  │ 消息队列    │  │  │ 态势分析引擎    │    │  │ 系统配置    │ │   │
-│  │  │ (Kafka)    │  │  │ (计算/聚合)     │    │  │ 日志审计    │ │   │
-│  │  └─────────────┘  │  └─────────────────┘    │  └─────────────┘ │   │
-│  └───────────────────┴──────────────────────────┴──────────────────┘   │
-└─────────────────────────────────────────────────────────────────────────┘
-                                    ▲
-                                    │ 内部 API 调用
-                                    ▼
-┌─────────────────────────────────────────────────────────────────────────┐
-│                           Web管理端 (React Admin)                        │
-│  ┌─────────────────────────────────────────────────────────────────┐    │
-│  │  登录页 │ 仪表盘 │ 用户管理 │ 数据源配置 │ 任务监控 │ 系统配置   │    │
-│  └─────────────────────────────────────────────────────────────────┘    │
-└─────────────────────────────────────────────────────────────────────────┘
-                                    ▲
-                                    │ PostgreSQL / Redis
-                                    ▼
-┌─────────────────────────────────────────────────────────────────────────┐
-│                           数据存储层                                      │
-│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐    │
-│  │ PostgreSQL  │  │ TimescaleDB │  │    Redis    │  │  MinIO      │    │
-│  │ (用户/配置) │  │ (时序数据)  │  │ (缓存/会话) │  │ (文件存储) │    │
-│  └─────────────┘  └─────────────┘  └─────────────┘  └─────────────┘    │
-└─────────────────────────────────────────────────────────────────────────┘
+┌─────────────────────────────────────────────────────────────────────┐
+│                         浏览器展示与运维层                            │
+│  ┌──────────────────────────────┐  ┌──────────────────────────────┐ │
+│  │ Web Earth                    │  │ React 运维台                  │ │
+│  │ frontend/public/earth        │  │ frontend/src                  │ │
+│  │ Three.js 地球 / HUD / 新闻    │  │ 数据源 / 告警 / AI 设置       │ │
+│  │ 国界精度 / 品牌内容配置       │  │ 提示词配置 / 用户与系统配置   │ │
+│  └──────────────────────────────┘  └──────────────────────────────┘ │
+└─────────────────────────────────────────────────────────────────────┘
+                       │ REST / WebSocket
+                       ▼
+┌─────────────────────────────────────────────────────────────────────┐
+│                       FastAPI 业务与编排后端                          │
+│  ┌────────────────────┐ ┌────────────────────┐ ┌─────────────────┐ │
+│  │ 数据 API 与认证     │ │ Earth 新闻增强      │ │ 告警与态势简报   │ │
+│  │ JWT / 权限 / 审计   │ │ 位置推断 / 本地化   │ │ BGP / 告警研判   │ │
+│  └────────────────────┘ └────────────────────┘ └─────────────────┘ │
+│  ┌────────────────────┐ ┌────────────────────┐ ┌─────────────────┐ │
+│  │ 系统运行配置        │ │ 默认提示词注册表     │ │ 未来 Agent Runtime│ │
+│  │ system_settings     │ │ 代码发布 + DB 覆盖  │ │ 工具/证据/工作流   │ │
+│  └────────────────────┘ └────────────────────┘ └─────────────────┘ │
+└─────────────────────────────────────────────────────────────────────┘
+        │ SQLAlchemy / Redis Stream            │ 纯净 LLM 调用
+        ▼                                      ▼
+┌──────────────────────────────┐      ┌──────────────────────────────┐
+│ PostgreSQL / Redis            │      │ aiprovider                   │
+│ 用户、配置、采集结果、新闻     │      │ provider + protocol adapter  │
+│ Stream、缓存、运行状态         │      │ OpenAI / MiniMax / Ollama 等 │
+└──────────────────────────────┘      └──────────────────────────────┘
+        ▲
+        │ 采集器 / 外部数据源
+        ▼
+┌─────────────────────────────────────────────────────────────────────┐
+│ RSS 新闻、BGP 观测、公开数据源、后续 WebSearch/OCR/语音识别等工具      │
+└─────────────────────────────────────────────────────────────────────┘
 ```
 
+架构边界:
+
+- `backend` 负责业务语义、证据收集、提示词选择、AI 任务编排、权限和数据落库。
+- `aiprovider` 只负责把纯净模型请求适配到不同供应商或协议，不内置具体业务提示词。
+- 默认提示词随代码发布并保存在 `backend/app/ai_tasks/default_prompts.json`，运维台可在数据库中保存覆盖值，重置时回到当前代码版本的默认提示词。
+- Earth 新闻保留英文原文，中文展示结果存入 `localizations`，前端默认展示 `zh-CN` 的 `display_title`、`display_summary` 和中文地域/状态文案。
+- Earth LLM 指令、语音识别、多角色态势研判属于后续 Agent Runtime 方向，计划见 [docs/plans/agents-earth-command-runtime-plan.md](/home/ray/dev/linkong/planet/docs/plans/agents-earth-command-runtime-plan.md)。
+
 ## 四大核心要素
 
 | 层级 | 要素 | 描述 |
@@ -87,11 +73,10 @@
 |------|------|------|
 | FastAPI | 0.109+ | Web 框架 |
 | SQLAlchemy | 2.0+ | ORM |
-| Alembic | - | 数据库迁移 |
-| Celery | 5.3+ | 任务队列 |
-| Redis | 7.0+ | 缓存/消息 |
-| Kafka | 3.0+ | 事件流 |
+| uv | - | Python 依赖与命令运行 |
+| Redis | 7.0+ | 缓存、Stream 与运行协调 |
 | PyJWT | - | 认证 |
+| APScheduler / 后台任务 | - | 采集、增强与运行时任务 |
 
 ### 前端 (React Admin)
 
@@ -102,6 +87,7 @@
 | Axios | HTTP 客户端 |
 | Socket.io-client | WebSocket 客户端 |
 | ECharts | 统计图表 |
+| Three.js | Earth 3D 地球渲染 |
 | Bun | 前端包管理与脚本运行 |
 
 前端工程统一使用 Bun：
@@ -110,22 +96,16 @@
 - 运行脚本使用 `bun run <script>`
 - 不使用 `npm`、`pnpm`、`yarn`
 
-### 虚幻引擎客户端
+### 大屏与 3D 展示方向
 
-| 组件 | 版本 | 用途 |
-|------|------|------|
-| Unreal Engine 5 | 5.3+ | 3D 渲染引擎 |
-| Cesium for Unreal | 1.5+ | 地理可视化 |
-| Niagara | - | 粒子系统 |
+当前发布优先使用浏览器 Web Earth。UE5 / Cesium for Unreal / Niagara 可作为后续物理大屏方向接入，但不是本地开发闭环的必需组件。
 
 ### 数据库
 
 | 组件 | 用途 |
 |------|------|
 | PostgreSQL 15+ | 关系数据 |
-| TimescaleDB | 时序数据扩展 |
-| Redis 7+ | 缓存/会话 |
-| MinIO | S3 兼容存储 |
+| Redis 7+ | 缓存、Stream、运行状态 |
 
 ### 部署
 
@@ -152,9 +132,9 @@
 | P0 | Epoch AI | 每小时 |
 | P0 | Hugging Face | 每 2 小时 |
 | P0 | GitHub | 每 4 小时 |
-| P0 每日 |
+| P0 | 海底光缆 / IXP / 卫星等基础设施数据 | 每日或按源刷新 |
 | P0 | PeeringDB | 每 2 小时 |
-| P1 | Cloudflare Radar | | TeleGeography | 每小时 |
+| P1 | Cloudflare Radar / TeleGeography | 每小时 |
 | P1 | CAIDA BGPStream | 每 15 分钟 |
 
 ## 项目结构
@@ -166,20 +146,18 @@
 │   │   ├── core/         # 核心配置
 │   │   ├── models/       # 数据模型
 │   │   ├── schemas/      # Pydantic 模型
-│   │   ├── services/     # 业务逻辑
-│   │   └── tasks/        # Celery 任务
+│   │   ├── services/     # 业务逻辑与 AI 任务编排
+│   │   └── ai_tasks/     # 默认提示词与 AI 任务定义
 │   └── tests/
+├── aiprovider/            # 独立模型供应商适配层
 ├── frontend/              # React 管理后台
 │   ├── src/
 │   │   ├── components/   # 组件
 │   │   ├── pages/        # 页面
 │   │   ├── services/     # API 服务
 │   │   └── store/        # 状态管理
-│   └── tests/
-├── unreal/                # UE5 大屏客户端
-│   ├── Content/
-│   ├── Source/
-│   └── Plugins/
+│   ├── public/earth/      # Web Earth 静态应用
+│   └── tests/             # 前端测试
 ├── data/                  # 数据文件
 ├── docs/                  # 文档
 ├── scripts/               # 脚本
@@ -191,10 +169,11 @@
 ## 快速启动
 
 ```bash
-# 新机器首次初始化
-./scripts/bootstrap-dev.sh
-# 会自动安装/检查 uv、bun，并同步 Python/前端依赖
+# 新机器或空项目首次初始化
+./planet.sh init
+# 会自动安装/检查 uv、bun，同步 Python/前端依赖
 # 会在缺少时生成 backend/.env、aiprovider/.env、frontend/.env.local
+# 会启动 PostgreSQL/Redis，并创建表、默认数据源和本地默认用户
 
 # 启动前后端服务
 ./planet.sh start
@@ -210,6 +189,9 @@
 
 # 查看服务状态
 ./planet.sh health
+
+# 删除容器、卷、镜像和本地编译状态，执行前需要输入 Y 确认
+./planet.sh destroy
 ```
 
 前端命令约定：
@@ -236,13 +218,15 @@ bun run build
 
 推荐按下面顺序排查和配置。
 
+端口占用、`iphlpsvc` / portproxy、摄像头和依赖问题的集中排障入口见 [常见问题](/home/ray/dev/linkong/planet/docs/technical/zh/faq.md)。
+
 ### 1. 在 WSL 中启动服务
 
 ```bash
 ./planet.sh start --allow-lan
 ```
 
-这会让前端监听 `0.0.0.0:3000`，后端监听 `0.0.0.0:8000`。
+这会让前端监听 `0.0.0.0:3000`，后端监听 `0.0.0.0:8000`，AI Provider 通过 Docker 发布到 `0.0.0.0:8010`。启动前脚本会检查这三个端口；如果 WSL/Linux 侧无法释放端口，并检测到 Windows 侧 listener 或旧 `portproxy`，会请求管理员 PowerShell 清理。
 
 ### 2. 先确认 WSL 内部服务正常
 
@@ -251,14 +235,16 @@ bun run build
 ```bash
 curl http://localhost:3000
 curl http://localhost:8000/health
-ss -ltnp | grep -E ':3000|:8000'
+curl http://localhost:8010/health
+ss -ltnp | grep -E ':3000|:8000|:8010'
 ```
 
 预期：
 
 - `3000` 返回前端 HTML
 - `8000/health` 返回健康检查 JSON
-- `ss` 中能看到 `0.0.0.0:3000` 和 `0.0.0.0:8000`
+- `8010/health` 返回 AI Provider 健康检查 JSON
+- `ss` 中能看到 `0.0.0.0:3000`、`0.0.0.0:8000` 和 `0.0.0.0:8010`，或 Docker 已发布 `8010`
 
 如果这一步不通，先不要继续做 Windows 转发。
 
@@ -269,42 +255,31 @@ ss -ltnp | grep -E ':3000|:8000'
 ```powershell
 curl http://localhost:3000
 curl http://localhost:8000/health
+curl http://localhost:8010/health
 ```
 
 在常见的 WSL2 开发环境下，Windows 通常可以直接通过 `localhost` 访问 WSL 中的服务。
 
-### 4. 如果需要让局域网设备访问，再做 Windows 端口转发
+### 4. 如果需要让局域网设备访问，清理端口和防火墙
 
-注意：下面的命令必须在“以管理员身份运行”的 PowerShell 中执行。
+`./planet.sh start --allow-lan` 不再启动额外的 Windows 端口转发进程。它直接让开发服务对 `3000` / `8000` / `8010` 开放，并在启动前尝试释放这些端口。端口被 Windows 侧 listener 或旧 `portproxy` 占用时，脚本会请求一次管理员 PowerShell 清理。
 
-先把 Windows 对外网卡上的 `3000` / `8000` 转发到 Windows 本机 `127.0.0.1`：
+如果以前手动配置过持久 `portproxy`，若自动请求被取消，可以手动清理，避免 `iphlpsvc` 继续占用端口：
 
 ```powershell
 netsh interface portproxy delete v4tov4 listenaddress=0.0.0.0 listenport=3000
 netsh interface portproxy delete v4tov4 listenaddress=0.0.0.0 listenport=8000
-
-netsh interface portproxy add v4tov4 listenaddress=0.0.0.0 listenport=3000 connectaddress=127.0.0.1 connectport=3000
-netsh interface portproxy add v4tov4 listenaddress=0.0.0.0 listenport=8000 connectaddress=127.0.0.1 connectport=8000
+netsh interface portproxy delete v4tov4 listenaddress=0.0.0.0 listenport=8010
 ```
 
-再放行 Windows 防火墙：
+脚本会检测 Windows 防火墙是否已放行 `3000` / `8000` / `8010`。如果缺少规则，会触发一次 Windows UAC 管理员 PowerShell 请求来自动创建。若自动请求被取消，也可以手动执行：
 
 ```powershell
 New-NetFirewallRule -DisplayName "WSL Planet 3000" -Direction Inbound -Action Allow -Protocol TCP -LocalPort 3000
 New-NetFirewallRule -DisplayName "WSL Planet 8000" -Direction Inbound -Action Allow -Protocol TCP -LocalPort 8000
+New-NetFirewallRule -DisplayName "WSL Planet 8010" -Direction Inbound -Action Allow -Protocol TCP -LocalPort 8010
 ```
 
-检查转发规则是否生效：
-
-```powershell
-netsh interface portproxy show all
-```
-
-预期能看到：
-
-- `0.0.0.0:3000 -> 127.0.0.1:3000`
-- `0.0.0.0:8000 -> 127.0.0.1:8000`
-
 ### 5. 查 Windows 局域网 IP，并让其他设备访问
 
 在 Windows PowerShell 中执行：
@@ -319,6 +294,8 @@ ipconfig
 
 - `http://<Windows局域网IP>:3000/earth`
 - `http://<Windows局域网IP>:3000/admin`
+- `http://<Windows局域网IP>:8000/health`
+- `http://<Windows局域网IP>:8010/health`
 
 例如：
 
@@ -327,7 +304,7 @@ ipconfig
 ### 6. 常见现象与判断
 
 - WSL 中 `curl localhost:3000` 能通，但 Windows 访问 `WSL 的局域网 IP:3000` 不通：这是正常现象之一，优先验证 Windows 的 `localhost:3000`
-- Windows `localhost:3000` 能通，但局域网设备访问 `Windows 局域网 IP:3000` 不通：通常缺少 `portproxy` 或防火墙放行
+- Windows `localhost:3000` 能通，但局域网设备访问 `Windows 局域网 IP:3000` 不通：通常是 Windows 防火墙、网络配置或旧 `portproxy` 残留
 - `whoami /groups` 中 `S-1-5-32-544` 显示 `deny only`：说明当前 PowerShell 不是提权管理员窗口
 
 ### 7. 本项目一次性验证顺序
@@ -336,10 +313,12 @@ ipconfig
 
 1. WSL 中执行 `curl http://localhost:3000`
 2. WSL 中执行 `curl http://localhost:8000/health`
-3. Windows 中执行 `curl http://localhost:3000`
-4. Windows 中执行 `curl http://localhost:8000/health`
-5. 管理员 PowerShell 配置 `portproxy` 和防火墙
-6. 用手机或其他电脑访问 `http://<Windows局域网IP>:3000/earth`
+3. WSL 中执行 `curl http://localhost:8010/health`
+4. Windows 中执行 `curl http://localhost:3000`
+5. Windows 中执行 `curl http://localhost:8000/health`
+6. Windows 中执行 `curl http://localhost:8010/health`
+7. 按脚本提示完成 Windows 防火墙或端口清理 UAC 请求
+8. 用手机或其他电脑访问 Windows 对外端口，例如 `http://<Windows局域网IP>:3000/earth`
 
 ## 启动容错参数
 
@@ -363,18 +342,27 @@ DATABASE_RETRY_INTERVAL=10 \
 - `AI_PROVIDER_START_MAX_RETRIES` / `AI_PROVIDER_RETRY_INTERVAL`: 控制 `aiprovider` 的构建/启动与容器重启自愈，默认 `3` 次、`5` 秒
 - `BACKEND_MAX_RETRIES`: 控制后端进程启动重试次数，默认 `3`
 - `FRONTEND_MAX_RETRIES`: 控制前端 dev server 启动重试次数，默认 `3`
-- `BACKEND_HEALTH_CHECK_ATTEMPTS` / `BACKEND_HEALTH_CHECK_INTERVAL`: 控制后端 HTTP 健康检查等待次数与间隔，默认 `10` 次、`2` 秒
+- `BACKEND_HEALTH_CHECK_ATTEMPTS` / `BACKEND_HEALTH_CHECK_INTERVAL`: 控制后端 HTTP 健康检查等待次数与间隔，默认 `60` 次、`2` 秒
 - `FRONTEND_HEALTH_CHECK_ATTEMPTS` / `FRONTEND_HEALTH_CHECK_INTERVAL`: 控制前端 HTTP 可访问检查等待次数与间隔，默认 `10` 次、`2` 秒
 - `AI_PROVIDER_HEALTH_CHECK_ATTEMPTS` / `AI_PROVIDER_HEALTH_CHECK_INTERVAL`: 控制 `aiprovider` HTTP 健康检查等待次数与间隔，默认 `10` 次、`2` 秒
 
-## AI 接口预留
+## AI 与智能体接口
 
-项目现在采用“两层”设计:
+项目现在采用“三段式”边界:
 
-- 主后端暴露稳定业务接口: `GET /api/v1/ai/provider/status`、`POST /api/v1/ai/situational-awareness/analyze`
-- 独立 `aiprovider` 服务负责适配具体模型供应商
+- `backend`: 暴露业务接口，负责选择任务提示词、组织证据、调用工具、保存 AI 设置和结果。
+- `aiprovider`: 暴露模型网关接口，只负责 provider / protocol 适配，不写入 BGP、新闻、告警等业务提示词。
+- 模型供应商: OpenAI 兼容、MiniMax、Anthropic、Ollama 或其他兼容网关。
 
-这样前端和业务代码不直接依赖 OpenAI、本地模型网关或其他订阅服务，后续切换部署方式只需要调整环境变量。
+这样前端和业务代码不直接依赖某个模型供应商，后续增加 Agent Runtime、Earth 一键 LLM 指令、语音识别或多角色态势研判时，也可以把业务工作流放在后端，而不是污染模型适配层。
+
+当前已落地的 AI 配置能力:
+
+- 运维台 AI 设置可维护 provider、模型、协议、超时、token 等运行配置。
+- 运维台 AI 设置中的“提示词”页可选择不同功能入口，手动覆盖提示词，并一键重置到默认值。
+- 默认提示词随代码发布，位于 [backend/app/ai_tasks/default_prompts.json](/home/ray/dev/linkong/planet/backend/app/ai_tasks/default_prompts.json)。
+- 覆盖值保存在数据库运行配置中，升级代码后可继续保留现场配置，也可重置到新版本默认提示词。
+- 态势摘要、告警研判、新闻本地化等入口应使用各自任务提示词；调用 `aiprovider` 时只传递当前任务所需的 `prompt` / `system_prompt`。
 
 主后端建议配置:
 
@@ -387,39 +375,33 @@ AI_PROVIDER_TIMEOUT_SECONDS=60
 `aiprovider` 服务建议配置:
 
 ```env
-AI_PROVIDER=openai_compatible
-AI_BASE_URL=https://api.openai.com/v1
+AI_PROVIDER=minimax
+AI_PROVIDER_API=anthropic-messages
+AI_BASE_URL=https://api.minimaxi.com/anthropic
 AI_API_KEY=your_api_key
-AI_MODEL=gpt-4o-mini
+AI_MODEL=MiniMax-M2.7
 AI_TIMEOUT_SECONDS=60
 AI_PROVIDER_SERVICE_TOKEN=change_me
 ```
 
-OpenAI 兼容场景推荐使用:
+推荐映射关系:
 
-- `AI_PROVIDER=openai_compatible`
+- `vLLM` / `LM Studio` / `One API`: `AI_PROVIDER=openai` + `AI_PROVIDER_API=openai-completions`
+- `MiniMax`: `AI_PROVIDER=minimax` + `AI_PROVIDER_API=anthropic-messages`
+- Claude 兼容网关: `AI_PROVIDER=anthropic` + `AI_PROVIDER_API=anthropic-messages`
+- `Ollama`: `AI_PROVIDER=ollama` + `AI_PROVIDER_API=ollama-generate`
 
-Claude 兼容场景推荐使用:
-
-- `AI_PROVIDER=anthropic`
-- `AI_PROVIDER=anthropic_compatible`
-- `AI_PROVIDER=claude_compatible`
-
-Ollama 原生场景推荐使用:
-
-- `AI_PROVIDER=ollama`
-
-比如 MiniMax 或其他 Claude 兼容网关，可以这样配置:
+比如 MiniMax 可以这样配置:
 
 ```env
-AI_PROVIDER=claude_compatible
-AI_BASE_URL=https://your-claude-compatible-endpoint.example.com
+AI_PROVIDER=minimax
+AI_PROVIDER_API=anthropic-messages
+AI_BASE_URL=https://api.minimaxi.com/anthropic
 AI_API_KEY=your_api_key
-AI_MODEL=your-claude-compatible-model
+AI_MODEL=MiniMax-M2.7
 AI_TIMEOUT_SECONDS=60
 AI_MAX_TOKENS=1200
 AI_ANTHROPIC_VERSION=2023-06-01
-AI_PROVIDER_SERVICE_TOKEN=change_me
 ```
 
 如果你要本地直接起模型适配层，项目里已经补了模板:
@@ -427,12 +409,6 @@ AI_PROVIDER_SERVICE_TOKEN=change_me
 - [aiprovider/.env.example](/home/ray/dev/linkong/planet/aiprovider/.env.example)
 - [docker-compose.local-model.yml](/home/ray/dev/linkong/planet/docker-compose.local-model.yml)
 
-推荐映射关系:
-
-- `vLLM` / `LM Studio` / `One API`: `AI_PROVIDER=openai_compatible`
-- `MiniMax` / Claude 兼容网关: `AI_PROVIDER=claude_compatible`
-- `Ollama`: `AI_PROVIDER=ollama`
-
 运行与调用补充:
 
 - `./planet.sh start` 默认会启动 `aiprovider`
@@ -442,11 +418,13 @@ AI_PROVIDER_SERVICE_TOKEN=change_me
 
 详细文档:
 
-- [docs/technical/agents-aiprovider.md](/home/ray/dev/linkong/planet/docs/technical/agents-aiprovider.md)
+- [docs/technical/zh/agents-aiprovider.md](/home/ray/dev/linkong/planet/docs/technical/zh/agents-aiprovider.md)
+- [docs/technical/en/agents-aiprovider.md](/home/ray/dev/linkong/planet/docs/technical/en/agents-aiprovider.md)
 - [aiprovider/README.md](/home/ray/dev/linkong/planet/aiprovider/README.md)
 - [docs/technical/frontend-layout-guidelines.md](/home/ray/dev/linkong/planet/docs/technical/frontend-layout-guidelines.md)
 - [docs/plans/frontend-ai-playground-development-plan.md](/home/ray/dev/linkong/planet/docs/plans/frontend-ai-playground-development-plan.md)
 - [docs/plans/agents-situational-awareness-foundation-plan.md](/home/ray/dev/linkong/planet/docs/plans/agents-situational-awareness-foundation-plan.md)
+- [docs/plans/agents-earth-command-runtime-plan.md](/home/ray/dev/linkong/planet/docs/plans/agents-earth-command-runtime-plan.md)
 
 ## 前端页面布局规范
 

TODO.md

@@ -1,45 +1,87 @@
 # TODO
 
-- [x] 把 BGP 观测站和异常点的 `hover/click` 手感再磨细一点
-- [x] 开始做 BGP 异常和海缆/区域的关联展示
-- [x] 做 Earth 侧的 `BGP activity layer`，让低 incident 密度时地图仍然有持续可感知的观测存在感
-- [x] 给 Earth BGP 补三层状态表达：`平稳观测态 / 局部波动态 / 事件活跃态`
-- [x] 把“当前无活跃事件”改造成“观测网络仍在运行、当前未发现聚合级事件”的状态表达
-- [x] 做 collector / region 近 15 分钟 activity score 聚合接口或动态聚合逻辑
-- [x] 把 Earth 的 BGP incident 改成 `紧凑事件核 + 向外扩张环形 pulse`，替换当前大面积 glow
-- [x] 为 BGP incident 建立符号系统：按事件类型用不同 marker，而不是都用同一种亮点
-- [x] 把 incident 地理定位从 `collector-centric` 改成 `prefix-centric`，优先使用 `prefix_geography`，其次 `prefix_scope`，再次 ASN 区域，最后才回退到观测区域质心
-- [x] 新增 `prefix_geography` 数据层，不再把 `prefix_scope` 当成 prefix 地理归属本身
-- [x] 接入 `IPtoASN / IPtoCountry` 作为 prefix-centric geography 的主数据源
-- [x] 接入 `OpenGeoFeed` 作为 prefix geography 的高质量覆盖/override 数据源
-- [x] 把 RIR delegated 设计成 prefix geography 的 fallback，而不是主来源
-- [ ] 为 `aiprovider` 建立 `provider -> api adapter -> compat policy` 的配置中心，优先落成 `json` 或 `yaml` 文件，运行时按 `provider/model` 读取兼容设置，而不是把专项兼容继续散落在 Python 分支里
-- [ ] 为市面上主流 AI 服务补专项兼容配置并固化到配置文件中，至少覆盖 `OpenAI / Anthropic / MiniMax / Ollama / Moonshot / DeepSeek / Qwen / GLM / Gemini / OpenRouter / vLLM / LM Studio / One API`
-- [ ] 在兼容配置中补齐可声明项：`api adapter`、`base_url pattern`、`auth header`、`thinking default`、`reasoning block mapping`、`stream path`、`tool-call capability`、`multimodal capability`、`provider-specific request patch`
-- [ ] 接入 `inetnum` / `inet6num` whois 作为比 RIR 更细粒度的后备层
-- [x] 在 activity layer 之后继续补 `route leak` 和 `path instability / flap` detector
-- [ ] 对 [frontend/public/earth/js/bgp.js](/home/ray/dev/linkong/planet/frontend/public/earth/js/bgp.js) 做按职责拆分的小重构，拆成 data / markers / overlays / animation，降低后续维护复杂度
-- [ ] 可选优化（非必做）：将 BGP incident/collector 标点改为 HTML marker（参考 worldmonitor 的 `htmlElementsData` 思路），实现近乎固定屏幕尺寸与更高密度可点击性
-- [ ] 保持 Earth 当前这批纯个人偏好设置继续走本地持久化：`旋转模式`、HUD 面板显示/隐藏、`地形透明度` 暂不升级到后端系统设置，避免把设备级偏好过早做成全局配置
-- [ ] 如果后续明确需要“账号级同步 Earth 偏好”，再单独设计 `Earth user preferences`：优先按用户维度而不是全局系统设置保存，并规划 `localStorage -> backend` 的平滑迁移策略
-- [ ] 为 Planet / Earth 补一个可用的日志查看系统：先明确前后端/AI Provider/采集任务的日志入口、最近日志聚合、筛选与 tail 能力，再决定是先做脚本级统一入口还是控制台内置日志面板
-- [ ] 重写控制台 UI，逐步抛弃 Ant Design，建立自有组件体系，并统一采用 `tabler.io` / Tabler Icons 作为控制台主图标库
-- [ ] 把 Earth 态势新闻源从 [earth_news.py](/home/ray/dev/linkong/planet/backend/app/services/earth_news.py) 的硬编码列表抽成可配置目录，优先保持当前“实时聚合”链路不变，只先解决新闻源不可配置的问题
-- [ ] 为 Earth 态势新闻设计后续采集器化方案：明确新闻数据模型、去重策略、区域映射、过期清理和 Earth/AI 复用方式，再决定何时把新闻从实时抓取升级成正式 collector
-- [ ] AIS v3.1：修复船只聚合完整性，`/geo/vessels` 合并 raw observation 聚合结果与 legacy `vessel_position + vessel_static` 最新结果，确保 BarentsWatch-only 船只不会因为 AISStream 子集存在而消失，并增加 raw/legacy/final unique MMSI 诊断统计
-- [ ] AIS v3.2：把 AISStream 从收满 `max_messages` 后结束的批采集改成长连接 streaming service，持续写入 raw observations，通过内部 `/ws` 的 `vessels` channel 推送新船、位置和航向增量，Earth 前端按 MMSI upsert marker
-- [ ] AIS v3.3：修正 AISStream 采集页面状态语义，使用 connecting/streaming/reconnecting/stopped 与 indeterminate 状态，展示运行时长、消息数、unique MMSI、message rate、最近消息和错误，不再用一次性 REST 进度条表示长连接
-- [ ] AIS v3.4：修复船只身份字段和名称聚合，MMSI/IMO/callsign 按字符串显示且不带千分位符；查询并列出所有仍以 MMSI 号码或 `MMSI <number>` 作为船名的记录，标注来源、最近观测、message types 和缺失原因，并把这批 fallback-name 船只纳入名称聚合修复集合
-- [ ] Earth Live Sync：建立统一态势实时同步链路，新增 `earth_summary` WS channel，任意采集器成功后广播轻量 summary invalidation，前端收到后重新拉 `/api/v1/visualization/geo/summary` 并更新 HUD；同时为 BGP 增加 `bgp` WS channel，使 BGP incidents/anomalies/collectors 在不刷新页面时也能 upsert 图层；卫星采集完成后触发 summary 刷新，必要时按 TLE 版本重新 hydrate 卫星数据
-- [ ] AIS v4：开放船只多源聚合策略配置，支持 source priority、字段级规则、freshness 窗口和高级保护开关；保存时校验未知字段、非法模式和危险动态字段锁定，并在聚合接口返回命中的配置版本
-- [ ] AIS v5：实现船舶资料 enrichment 与冲突治理，按 `mmsi + imo + name + callsign` 异步补充船型细分、AIS 大类、旗国、尺寸、建造年份、运营方和图片缓存；详情面板展示缓存资料和字段来源，不在实时 AIS 请求链路现场抓第三方页面
-- [ ] 为 Earth 地球表面增加一层与基础纹理对齐的材质/纹理 overlay，并在同层叠加国界轮廓参考线；要求国界线与底图稳定对齐，且 hover 到国家轮廓时能高亮当前国家，便于校准地表和增强交互
-- [ ] 把 Earth 新闻接入通用巡航队列：按新闻发生地和时间排序生成巡航目标，巡航聚焦到新闻事件时显示对应新闻卡片，并保持实现边界为“通用巡航层 + 新闻业务适配层”，不要再把新闻逻辑直接耦合回 `main.js` 状态机
-- [ ] 为未知位置的算力中心建立分层坐标补全链路：优先 `精确坐标 > 站点/园区命中 > 城市 > 州/省 > 国家内主要算力城市 > 国家质心`，并把每次回退的 `confidence / reason / precision` 明确写进统一 GeoJSON
-- [ ] 为算力中心补一份可维护的本地位置注册表，例如 `canonical_name / aliases / operator / country / region / city / lat / lon / confidence / source_note`，避免把地点知识长期硬编码在 `visualization.py`
-- [ ] 增强 `epoch_ai_gpu` 和相关算力采集器的源页面解析：即使公开 API 不给坐标，也继续尝试从详情页、HTML、内嵌 JSON、schema.org、OpenGraph、脚本变量和 PDF/新闻稿链接里抽地点线索
-- [ ] 为未知位置算力中心增加外部富化策略评估：可选接入公开知识源或搜索兜底，只抓“站点名/园区名/城市名”级别线索，不直接抓经纬度结论，并把结果作为候选证据而不是真值
-- [ ] 为算力中心建立 `operator / cluster name / facility alias` 归一化层，先解决 `xAI / Colossus / Memphis`、`OpenAI / Stargate`、`CoreWeave`、`Lambda`、`Crusoe` 这类同一对象多种写法导致的地点匹配失败
-- [ ] 为估算位置增加更细的视觉和产品表达：除了问号角标，还要支持 tooltip/详情中的“估算依据”“精度级别”“最后核验时间”，并允许在设置中单独开关“仅看精确位置”
-- [ ] 为国家级估算点设计更合理的落点策略：优先落在“该国主要算力/数据中心城市候选集”而不是几何质心，必要时同国多节点做稳定散列分配，避免大量节点堆在荒漠或海上
-- [ ] 为未知位置算力中心建立人工校验工作流：支持导出待核验清单、记录人工确认结果，并把人工确认反哺到位置注册表，逐步减少问号点比例
+This file is the active backlog only. Completed history belongs in `docs/CHANGELOG.md`; detailed designs belong in `docs/plans/`.
+
+## Earth
+
+- [ ] Earth AI command entry: merge natural-language and speech-triggered LLM commands into the existing Earth search panel as described in [Agent Runtime, Earth LLM Command, And Speech Entry Plan](/home/ray/dev/linkong/planet/docs/plans/agents-earth-command-runtime-plan.md).
+- [ ] Earth action executor: implement safe visualization actions for layer toggles, batch highlights, filters, focus, result panels, and clear-highlight behavior.
+- [ ] Earth entity matching: support stable entity ids and batch matching for Beidou satellites, mainland China compute centers, BGP, news, vessels, and cables.
+- [ ] Replace debug GeoJSON boundary tiles with the real `earth-boundaries-china-pov-v1.pmtiles` production artifact after audited admin-0 / coastline / claim-line sources and the PMTiles toolchain are available.
+- [ ] Import authoritative China POV / coastline / claim-line source packages through the three standard Earth boundary source collectors, then rebuild a versioned PMTiles artifact so highest zoom `8-10` preserves trusted source geometry instead of seed data.
+- [ ] Earth boundary data: acquire or generate auditable China POV geometry for Zangnan, Aksai Chin, Taiwan/Penghu, Diaoyu Dao and affiliated islands, Chiwei Yu, South China Sea islands, Kosovo, Gaza, and the official dashed maritime claim line before implementing final visual changes.
+- [ ] Earth high-resolution basemap tiles: implement the viewport-loaded imagery layer described in [Earth High Resolution Basemap Tiles Plan](/home/ray/dev/linkong/planet/docs/plans/earth-high-resolution-basemap-tiles-plan.md), using high-precision coastline as the alignment reference instead of replacing the globe with one huge texture.
+- [ ] Presentation controller ownership: replace the singleton card fallback in [presentation-controller.js](/home/ray/dev/linkong/planet/frontend/public/earth/js/presentation-controller.js) with a presentation/card token check before BGP/News migrate onto the shared controller, so connectors only attach to their owning card.
+- [ ] BGP frontend maintainability: split [bgp.js](/home/ray/dev/linkong/planet/frontend/public/earth/js/bgp.js) by responsibility into data loading, marker rendering, overlays, and animation once the current interaction behavior is stable.
+- [ ] Optional BGP marker experiment: evaluate HTML markers for BGP incident/collector points if WebGL marker density or fixed screen-size clickability becomes a real blocker.
+- [ ] Earth news cruise: connect Earth news to the generic cruise queue via a news adapter rather than coupling news-specific sequencing into `main.js`.
+
+## Compute Centers And Location
+
+- [ ] Unknown compute-center locations: continue reducing unresolved records through the shared location pipeline, with confidence, precision, reason, and verification date preserved in GeoJSON/details.
+- [ ] Compute-center registry: keep expanding the local canonical location registry with `canonical_name`, aliases, operator, country/region/city, coordinates, confidence, and source notes.
+- [ ] Compute-center enrichment: improve source-page parsing for Epoch AI and related collectors by extracting location clues from detail pages, embedded JSON, schema.org, OpenGraph, script variables, PDFs, and press releases.
+- [ ] Compute-center identity normalization: normalize operator / cluster / facility aliases such as `xAI / Colossus / Memphis`, `OpenAI / Stargate`, `CoreWeave`, `Lambda`, and `Crusoe`.
+- [ ] Compute-center manual review: add an export/review/import workflow for unresolved or estimated locations and feed confirmed results back into the registry.
+
+## AIS / Vessels
+
+- [ ] AIS aggregation strategy v4: expose source priority, field-level merge rules, freshness windows, and protected dynamic-field rules in configuration, with validation and strategy version returned by vessel APIs.
+- [ ] AIS vessel enrichment v5: add asynchronous vessel profile enrichment for ship type detail, AIS class, flag, dimensions, build year, operator, and cached media. Do not fetch third-party pages in the realtime AIS request path.
+- [ ] AIS identity cleanup: continue identifying vessels whose display name is only `MMSI <number>` and backfill names from AISStream static messages, BarentsWatch static fields, or enrichment cache.
+
+## AI Provider And Agents
+
+- [ ] Unified integration config schema: implement the shared low-code schema engine for datasource, AI Provider, Web Search, and OCR configuration described in [Integration Config Schema System Plan](/home/ray/dev/linkong/planet/docs/plans/integration-config-schema-system-plan.md).
+- [ ] AI provider routing: finish the OpenClaw-style provider/model routing refactor described in [AI Provider OpenClaw-Style Routing Plan](/home/ray/dev/linkong/planet/docs/plans/ai-provider-openclaw-style-routing-plan.md), so model-specific transport rules live in provider metadata rather than runtime hardcoding.
+- [ ] AI provider catalog: replace the temporary `model_provider_apis` bridge with structured `models_metadata`, discovery descriptors, and incremental model sync with stale marking.
+- [ ] AI provider connectivity: keep the plug action as lightweight network/auth/model-directory validation only, and keep real generation tests inside Playground or explicit “trial run” actions.
+- [ ] Agent runtime foundation: add auditable agent runs, steps, evidence, proposals, and the Agent operations UI described in [Agent Runtime, Earth LLM Command, And Speech Entry Plan](/home/ray/dev/linkong/planet/docs/plans/agents-earth-command-runtime-plan.md).
+- [ ] Agent tool protocol: add backend JSON tool-call fallback, optional provider-native tool compatibility, tool whitelist validation, and policy-gated proposal application.
+- [ ] Speech/ASR integration for agents: add provider-neutral transcription settings and API, defaulting to Whisper-compatible API providers while keeping text commands usable when ASR is unavailable.
+- [ ] Earth voice wake: add device-local configurable wake-word preferences, microphone fallback states, and post-wake instruction upload for Earth commands.
+- [ ] AI provider compatibility center: move provider/model compatibility rules into a JSON/YAML config read by runtime, instead of continuing to scatter provider-specific branches through Python code.
+- [ ] Provider compatibility coverage: add explicit config for OpenAI, Anthropic, MiniMax, Ollama, Moonshot, DeepSeek, Qwen, GLM, Gemini, OpenRouter, vLLM, LM Studio, and One API.
+- [ ] Compatibility schema: cover adapter type, base URL pattern, auth header, thinking/reasoning defaults, stream path, tool-call capability, multimodal capability, and provider-specific request patches.
+- [ ] BGP geography fallback: evaluate `inetnum` / `inet6num` whois as a finer fallback layer after `prefix_geography`, `OpenGeoFeed`, and RIR delegated data.
+
+## Platform
+
+- [ ] Earth preferences scope: keep current device-local Earth preferences in `localStorage`; only design backend user preferences if account-level synchronization becomes a real product requirement.
+- [ ] System logs: finish a usable Planet log viewing flow that covers backend, frontend, AI Provider, and collector/task logs, with filtering and tailing.
+- [ ] Console UI modernization: gradually replace Ant Design with Planet-owned components and a consistent Tabler Icons based icon system.
+- [ ] Earth live sync: design a unified realtime invalidation path for summary/BGP/satellite updates if polling and current WebSocket channels become insufficient.
+
+## Archive
+
+Archived items stay here so old context is not lost. Completed items remain checked; obsolete, invalid, or superseded items stay unchecked and include the reason.
+
+### Completed
+
+- [x] Implemented the high-precision country boundary tile framework from [Earth High Precision Boundary Tiles Plan](/home/ray/dev/linkong/planet/docs/plans/earth-high-precision-boundary-tiles-plan.md): static vector tile builder, versioned seed output, frontend bbox tile loader, debounce, in-flight dedupe, and LRU cache.
+- [x] Added the `pmtiles-mvt` frontend tile provider contract, MVT decoder dependencies, static PMTiles Nginx handling, collector artifact registration, production readiness check, and user operation docs for Earth boundaries.
+- [x] Split Earth boundary ingestion into standard source collectors (`earth_admin0_boundaries`, `earth_coastline`, `earth_claim_lines`) plus the downstream `earth_boundary_tiles` PMTiles builder.
+- [x] Refined BGP observer and anomaly `hover/click` feel.
+- [x] Added BGP anomaly relationship display with cables / regions.
+- [x] Added the Earth BGP activity layer so the map still feels alive when incident density is low.
+- [x] Added BGP state expression for stable observation, local fluctuation, and active incident states.
+- [x] Reframed "no active incident" as "observation network is running; no aggregate incident detected".
+- [x] Added collector / region recent activity scoring.
+- [x] Replaced oversized BGP incident glow with compact incident core plus outward pulse rings.
+- [x] Added BGP incident symbol types instead of using one generic bright marker.
+- [x] Switched BGP incident geography from collector-centric to prefix-centric priority.
+- [x] Added `prefix_geography` as a separate data layer instead of treating `prefix_scope` as prefix geography.
+- [x] Added IPtoASN / IPtoCountry as the main prefix-centric geography source.
+- [x] Added OpenGeoFeed as a high-quality prefix geography override source.
+- [x] Made RIR delegated data a prefix geography fallback rather than the primary source.
+- [x] Added route leak and path instability / flap detectors after the activity layer work.
+
+### Obsolete Or Superseded
+
+- [ ] AIS v3.1 old `/geo/vessels` full-merge requirement. Superseded by `/api/v1/vessels/snapshot`, controlled legacy fallback, and diagnostics in the AIS aggregation plan.
+- [ ] AIS v3.2 old framing of AISStream as a batch collector that needed conversion. Superseded by the implemented long-lived AISStream collector and realtime stream UI.
+- [ ] AIS v3.3 old one-shot REST progress semantics for AISStream. Superseded by realtime stream status handling.
+- [ ] AIS v3.4 broad identity cleanup wording. Folded into the active AIS identity cleanup and v5 enrichment tasks.
+- [ ] Earth surface material overlay for boundary calibration. Superseded by the high-precision boundary tile plan; future work must use source-faithful boundary/coastline data rather than overlay calibration against the coarse base map.
+- [ ] Hardcoded Earth news source extraction as a standalone task. Superseded by the broader Earth news source configuration and collector plans.
+- [ ] Country-level compute-center fallback placement as a standalone task. Superseded by the shared location pipeline and registry/manual-review backlog.

VERSION

@@ -1 +1 @@
-0.49.0
+0.66.2

aiprovider/.env.example

@@ -32,6 +32,15 @@ AI_API_KEY=sk-cp-change-me
 AI_MAX_TOKENS=1200
 AI_ANTHROPIC_VERSION=2023-06-01
 
+# Optional provider-specific keys used by Settings fallback before AI_API_KEY
+# MINIMAX_API_KEY=sk-cp-change-me
+# OPENAI_API_KEY=sk-change-me
+# ANTHROPIC_API_KEY=sk-ant-change-me
+# DEEPSEEK_API_KEY=sk-change-me
+# DASHSCOPE_API_KEY=sk-change-me
+# MOONSHOT_API_KEY=sk-change-me
+# OPENROUTER_API_KEY=sk-or-change-me
+
 # OpenAI-compatible example (vLLM / LM Studio / One API / local gateway)
 # AI_PROVIDER=openai
 # AI_PROVIDER_API=openai-completions

aiprovider/Dockerfile

@@ -2,10 +2,14 @@
 
 ARG PYTHON_IMAGE=python:3.14-slim
 ARG UV_IMAGE=ghcr.io/astral-sh/uv:latest
+ARG AI_PROVIDER_BUILD_FINGERPRINT=unknown
 
 FROM ${UV_IMAGE} AS uv
 FROM ${PYTHON_IMAGE}
 
+ARG AI_PROVIDER_BUILD_FINGERPRINT
+LABEL planet.aiprovider.build-fingerprint="${AI_PROVIDER_BUILD_FINGERPRINT}"
+
 COPY --from=uv /uv /uvx /bin/
 
 WORKDIR /app
@@ -15,16 +19,22 @@ ENV PYTHONUNBUFFERED=1
 ENV UV_COMPILE_BYTECODE=1
 ENV UV_LINK_MODE=copy
 
+RUN mkdir -p /root/.config/uv
+
 RUN apt-get update && apt-get install -y --no-install-recommends \
     curl \
     && rm -rf /var/lib/apt/lists/*
 
 COPY pyproject.toml uv.lock /app/
 RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=secret,id=planet_uv_config,target=/root/.config/uv/uv.toml,required=false \
     uv sync --frozen --no-dev
 
 COPY aiprovider /app/aiprovider
 
 EXPOSE 8010
 
-CMD ["uv", "run", "--frozen", "--no-dev", "--project", "/app", "python", "-m", "uvicorn", "aiprovider.main:app", "--host", "0.0.0.0", "--port", "8010", "--reload"]
+HEALTHCHECK --interval=30s --timeout=5s --retries=3 \
+    CMD curl -fsS http://127.0.0.1:8010/health >/dev/null || exit 1
+
+CMD ["uv", "run", "--frozen", "--no-dev", "--project", "/app", "python", "-m", "uvicorn", "aiprovider.main:app", "--host", "0.0.0.0", "--port", "8010"]

aiprovider/config.py

@@ -17,9 +17,6 @@ class Settings(BaseSettings):
     AI_HTTP_RETRY_ATTEMPTS: int = 2
     AI_MAX_TOKENS: int = 1200
     AI_ANTHROPIC_VERSION: str = "2023-06-01"
-    AI_ANALYSIS_SYSTEM_PROMPT: str = (
-        "你是态势感知分析助手。请基于输入的上下文、观测与约束，输出结构化、克制、可执行的分析。"
-    )
 
     AI_PROVIDER_SERVICE_TOKEN: str = ""
 

aiprovider/main.py

@@ -45,6 +45,7 @@ def get_provider_service(
     x_ai_model: str | None = Header(default=None),
     x_ai_max_tokens: str | None = Header(default=None),
     x_ai_anthropic_version: str | None = Header(default=None),
+    x_ai_model_provider_apis: str | None = Header(default=None),
 ) -> ProviderService:
     overrides = {
         "provider": x_ai_provider,
@@ -53,6 +54,7 @@ def get_provider_service(
         "api_key": x_ai_api_key,
         "model": x_ai_model,
         "anthropic_version": x_ai_anthropic_version,
+        "model_provider_apis": x_ai_model_provider_apis,
     }
     if x_ai_max_tokens:
         overrides["max_tokens"] = x_ai_max_tokens

aiprovider/provider_service.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import asyncio
+import json
 from typing import Any
 
 import httpx
@@ -14,7 +15,6 @@ from aiprovider.schemas import (
     SituationalAnalysisResponse,
 )
 
-
 def _normalize_provider(value: str) -> str:
     return (value or "disabled").strip().lower()
 
@@ -62,7 +62,9 @@ class ProviderService:
         self.anthropic_version = str(
             overrides.get("anthropic_version") or settings.AI_ANTHROPIC_VERSION
         )
-        self.system_prompt = settings.AI_ANALYSIS_SYSTEM_PROMPT
+        self.model_provider_apis = self._parse_model_provider_apis(
+            overrides.get("model_provider_apis")
+        )
 
     def get_status(self) -> AIProviderStatusResponse:
         enabled = self.provider != "disabled"
@@ -94,16 +96,23 @@ class ProviderService:
 
         prompt = self._build_prompt(payload)
 
-        if self.provider_api == "openai-completions":
-            data = await self._request_openai_compatible(model, prompt)
+        provider_api = self._resolve_model_provider_api(model)
+
+        if provider_api == "openai-completions":
+            data = await self._request_openai_compatible(model, prompt, payload.system_prompt)
             content = self._extract_openai_content(data)
             content_blocks = self._extract_openai_blocks(data)
-        elif self.provider_api == "anthropic-messages":
-            data = await self._request_anthropic_messages(model, prompt, payload.thinking)
+        elif provider_api == "anthropic-messages":
+            data = await self._request_anthropic_messages(
+                model,
+                prompt,
+                payload.thinking,
+                payload.system_prompt,
+            )
             content = self._extract_anthropic_content(data)
             content_blocks = self._extract_anthropic_blocks(data)
-        elif self.provider_api == "ollama-generate":
-            data = await self._request_ollama(model, prompt)
+        elif provider_api == "ollama-generate":
+            data = await self._request_ollama(model, prompt, payload.system_prompt)
             content = self._extract_ollama_content(data)
             content_blocks = self._extract_ollama_blocks(data)
         else:
@@ -128,6 +137,26 @@ class ProviderService:
     def _requires_api_key(self) -> bool:
         return self.provider_api != "ollama-generate"
 
+    def _resolve_model_provider_api(self, model: str) -> str:
+        return self.model_provider_apis.get(model) or self.provider_api
+
+    def _parse_model_provider_apis(self, value: Any) -> dict[str, str]:
+        if isinstance(value, dict):
+            raw = value
+        elif isinstance(value, str) and value.strip():
+            try:
+                parsed = json.loads(value)
+            except json.JSONDecodeError:
+                return {}
+            raw = parsed if isinstance(parsed, dict) else {}
+        else:
+            raw = {}
+        return {
+            str(model): _normalize_provider_api(str(provider_api))
+            for model, provider_api in raw.items()
+            if model and provider_api
+        }
+
     def _build_prompt(self, payload: SituationalAnalysisRequest) -> str:
         sections = [
             f"任务标题:\n{payload.title}",
@@ -139,19 +168,28 @@ class ProviderService:
             sections.append("约束条件:\n" + "\n".join(f"- {item}" for item in payload.constraints))
         if payload.context:
             sections.append(f"附加上下文:\n{payload.context}")
-        sections.append(
-            "请输出: 1) 态势摘要 2) 关键风险 3) 研判依据 4) 建议动作 5) 还缺少的数据。"
-        )
         return "\n\n".join(sections)
 
-    async def _request_openai_compatible(self, model: str, prompt: str) -> dict[str, Any]:
+    def _resolve_system_prompt(self, system_prompt: str | None) -> str | None:
+        resolved = str(system_prompt or "").strip()
+        return resolved or None
+
+    async def _request_openai_compatible(
+        self,
+        model: str,
+        prompt: str,
+        system_prompt: str | None = None,
+    ) -> dict[str, Any]:
+        messages = []
+        resolved_system_prompt = self._resolve_system_prompt(system_prompt)
+        if resolved_system_prompt:
+            messages.append({"role": "system", "content": resolved_system_prompt})
+        messages.append({"role": "user", "content": prompt})
         request_body = {
             "model": model,
-            "messages": [
-                {"role": "system", "content": self.system_prompt},
-                {"role": "user", "content": prompt},
-            ],
+            "messages": messages,
             "temperature": 0.2,
+            "max_tokens": self.max_tokens,
         }
         return await self._post(
             path="/chat/completions",
@@ -167,10 +205,10 @@ class ProviderService:
         model: str,
         prompt: str,
         thinking: dict[str, Any] | None = None,
+        system_prompt: str | None = None,
     ) -> dict[str, Any]:
         request_body = {
             "model": model,
-            "system": self.system_prompt,
             "messages": [
                 {
                     "role": "user",
@@ -185,6 +223,9 @@ class ProviderService:
             "max_tokens": self.max_tokens,
             "temperature": 0.2,
         }
+        resolved_system_prompt = self._resolve_system_prompt(system_prompt)
+        if resolved_system_prompt:
+            request_body["system"] = resolved_system_prompt
         resolved_thinking = self._resolve_anthropic_thinking(thinking)
         if resolved_thinking:
             request_body["thinking"] = resolved_thinking
@@ -218,19 +259,28 @@ class ProviderService:
         model: str,
         prompt: str,
         thinking: dict[str, Any] | None = None,
+        system_prompt: str | None = None,
     ) -> dict[str, Any]:
-        return await self._request_anthropic_messages(model, prompt, thinking)
+        return await self._request_anthropic_messages(model, prompt, thinking, system_prompt)
 
-    async def _request_ollama(self, model: str, prompt: str) -> dict[str, Any]:
+    async def _request_ollama(
+        self,
+        model: str,
+        prompt: str,
+        system_prompt: str | None = None,
+    ) -> dict[str, Any]:
         request_body = {
             "model": model,
             "stream": False,
-            "system": self.system_prompt,
             "prompt": prompt,
             "options": {
                 "temperature": 0.2,
+                "num_predict": self.max_tokens,
             },
         }
+        resolved_system_prompt = self._resolve_system_prompt(system_prompt)
+        if resolved_system_prompt:
+            request_body["system"] = resolved_system_prompt
         return await self._post(
             path="/api/generate",
             headers={
@@ -289,13 +339,19 @@ class ProviderService:
         message = choices[0].get("message") or {}
         content = message.get("content")
         if isinstance(content, str):
-            return content
+            if content:
+                return content
+            reasoning_content = message.get("reasoning_content")
+            return reasoning_content if isinstance(reasoning_content, str) else ""
         if isinstance(content, list):
             return "".join(
                 item.get("text", "")
                 for item in content
                 if isinstance(item, dict)
             )
+        reasoning_content = message.get("reasoning_content")
+        if isinstance(reasoning_content, str):
+            return reasoning_content
         return ""
 
     def _extract_openai_blocks(self, payload: dict[str, Any]) -> list[AIContentBlock]:
@@ -306,9 +362,14 @@ class ProviderService:
         message = choices[0].get("message") or {}
         content = message.get("content")
         if isinstance(content, str):
-            return [AIContentBlock(type="text", text=content)]
+            blocks = [AIContentBlock(type="text", text=content)] if content else []
+            reasoning_content = message.get("reasoning_content")
+            if isinstance(reasoning_content, str) and reasoning_content:
+                blocks.append(AIContentBlock(type="thinking", thinking=reasoning_content))
+            return blocks
         if not isinstance(content, list):
-            return []
+            reasoning_content = message.get("reasoning_content")
+            return [AIContentBlock(type="thinking", thinking=reasoning_content)] if isinstance(reasoning_content, str) and reasoning_content else []
 
         blocks: list[AIContentBlock] = []
         for item in content:
@@ -321,7 +382,11 @@ class ProviderService:
                     metadata={k: v for k, v in item.items() if k not in {"type", "text"}},
                 )
             )
+        reasoning_content = message.get("reasoning_content")
+        if isinstance(reasoning_content, str) and reasoning_content:
+            blocks.append(AIContentBlock(type="thinking", thinking=reasoning_content))
         return blocks
+
     def _extract_anthropic_content(self, payload: dict[str, Any]) -> str:
         content = payload.get("content")
         if isinstance(content, str):

aiprovider/schemas.py

@@ -13,10 +13,11 @@ class AIContentBlock(BaseModel):
 
 class SituationalAnalysisRequest(BaseModel):
     title: str = Field(..., min_length=1, max_length=200)
-    objective: str = Field(..., min_length=1, max_length=1000)
+    objective: str = Field(..., min_length=1, max_length=20000)
     context: dict[str, Any] = Field(default_factory=dict)
     observations: list[str] = Field(default_factory=list)
     constraints: list[str] = Field(default_factory=list)
+    system_prompt: str | None = Field(default=None, max_length=8000)
     preferred_model: str | None = Field(default=None, max_length=200)
     thinking: dict[str, Any] | None = None
 

backend/Dockerfile

@@ -1,3 +1,5 @@
+# syntax=docker/dockerfile:1.7
+
 ARG PYTHON_IMAGE=python:3.14-slim
 ARG UV_IMAGE=ghcr.io/astral-sh/uv:latest
 
@@ -12,17 +14,25 @@ ENV PYTHONDONTWRITEBYTECODE=1
 ENV PYTHONUNBUFFERED=1
 ENV UV_COMPILE_BYTECODE=1
 ENV UV_LINK_MODE=copy
+ENV PYTHONPATH=/app/backend
+
+RUN mkdir -p /root/.config/uv
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     curl \
     && rm -rf /var/lib/apt/lists/*
 
 COPY pyproject.toml uv.lock /app/
-RUN uv sync --frozen --no-dev
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=secret,id=planet_uv_config,target=/root/.config/uv/uv.toml,required=false \
+    uv sync --frozen --no-dev
 
 COPY backend /app/backend
 COPY VERSION /app/VERSION
 
 EXPOSE 8000
 
-CMD ["uv", "run", "--frozen", "--no-dev", "--project", "/app", "python", "-m", "uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]
+HEALTHCHECK --interval=30s --timeout=5s --retries=3 \
+    CMD curl -fsS http://127.0.0.1:8000/health >/dev/null || exit 1
+
+CMD ["uv", "run", "--frozen", "--no-dev", "--project", "/app", "python", "-m", "uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

backend/app/ai_tasks/__init__.py

@@ -0,0 +1,2 @@
+"""AI task prompt registry and runtime helpers."""
+

backend/app/ai_tasks/default_prompts.json

@@ -0,0 +1,74 @@
+[
+  {
+    "key": "earth.news.enrich",
+    "label": "Earth 新闻汉化与定位",
+    "group": "Earth 新闻",
+    "version": "2026-05-16.2",
+    "system_prompt": "",
+    "prompt": "Return exactly one strict JSON object with a location object and a localizations object. Infer the most likely physical event location and produce a faithful Simplified Chinese title plus a one-sentence newswire-style Chinese summary based only on the supplied RSS headline, description, source, and date. The summary should read like a concise breaking-news lead, not a label, slogan, or keyword headline."
+  },
+  {
+    "key": "alerts.brief",
+    "label": "系统告警研判",
+    "group": "告警研判",
+    "version": "2026-05-16.1",
+    "system_prompt": "你是告警研判助手。请基于输入的告警事实、上下文与约束，输出结构化、克制、可执行的值班研判；明确区分事实、推断与建议，不要夸大证据不足的风险。",
+    "prompt": "基于当前告警总量、严重度、状态、数据源分布与最近告警摘录，生成一份面向值班人员的简明告警态势简报，突出待处理风险、告警集中点和优先动作。"
+  },
+  {
+    "key": "alerts.situational.brief",
+    "label": "跨模块态势告警研判",
+    "group": "告警研判",
+    "version": "2026-05-16.1",
+    "system_prompt": "你是告警研判助手。请基于输入的告警事实、上下文与约束，输出结构化、克制、可执行的值班研判；明确区分事实、推断与建议，不要夸大证据不足的风险。",
+    "prompt": "综合系统告警、BGP incidents、BGP anomalies 与近期 BGP AI 简报，生成一份面向值班人员的态势告警简报，指出当前最需要关注的风险域、跨模块联动迹象和优先动作。"
+  },
+  {
+    "key": "bgp.brief",
+    "label": "BGP 态势简报",
+    "group": "BGP",
+    "version": "2026-05-16.2",
+    "system_prompt": "你是 BGP 值班分析师。请直接输出面向值班人员的中文 Markdown 简报，只写最终研判内容；不要复述用户需求、提示词、写作计划、字段清单或“我将如何回答”。",
+    "prompt": "基于当前 BGP incidents、anomalies、原始观测事件、观测站覆盖与 prefix geography 证据，生成一份面向操作员的简明态势简报，突出区域热点、观测偏差、当前风险、证据和优先动作。"
+  },
+  {
+    "key": "location.factcheck.normalize",
+    "label": "位置事实核查结构化",
+    "group": "位置解析",
+    "version": "2026-05-16.1",
+    "system_prompt": "",
+    "prompt": "Convert the supplied location factcheck text into exactly one strict JSON object. Extract only facts present in the text or original query."
+  },
+  {
+    "key": "location.factcheck.resolve",
+    "label": "位置事实核查兜底",
+    "group": "位置解析",
+    "version": "2026-05-16.1",
+    "system_prompt": "",
+    "prompt": "Return exactly one JSON object for the most likely physical location. Use only fact-checkable public knowledge; return null fields rather than guessing when evidence is weak."
+  },
+  {
+    "key": "datasource.mapping",
+    "label": "数据源映射生成",
+    "group": "采集配置",
+    "version": "2026-05-16.1",
+    "system_prompt": "",
+    "prompt": "Return only JSON for a deterministic mapping DSL. The JSON must contain source.items_path and fields. Do not include prose or code."
+  },
+  {
+    "key": "credential.guide",
+    "label": "采集器凭据教程",
+    "group": "采集配置",
+    "version": "2026-05-16.1",
+    "system_prompt": "",
+    "prompt": "生成一份中文采集器凭据配置教程。只能根据 context.search_evidence 中的来源生成教程；如果证据不足，明确说明需要以官方页面为准。"
+  },
+  {
+    "key": "ai.connection_test",
+    "label": "AI Provider 连接测试",
+    "group": "运维测试",
+    "version": "2026-05-16.1",
+    "system_prompt": "",
+    "prompt": "Reply OK."
+  }
+]

backend/app/ai_tasks/prompts.py

@@ -0,0 +1,182 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from datetime import UTC, datetime
+import json
+from functools import lru_cache
+from pathlib import Path
+from typing import Any
+
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.models.system_setting import SystemSetting
+
+AI_PROMPTS_CATEGORY = "ai_prompts"
+DEFAULT_PROMPTS_PATH = Path(__file__).with_name("default_prompts.json")
+
+
+@dataclass(frozen=True)
+class AIPromptDefinition:
+    key: str
+    label: str
+    group: str
+    version: str
+    system_prompt: str
+    prompt: str
+
+
+@dataclass(frozen=True)
+class EffectiveAIPrompt:
+    key: str
+    label: str
+    group: str
+    version: str
+    default_system_prompt: str
+    default_prompt: str
+    system_prompt: str
+    prompt: str
+    is_custom: bool
+    updated_at: str | None = None
+
+
+@lru_cache(maxsize=1)
+def list_prompt_definitions() -> tuple[AIPromptDefinition, ...]:
+    raw_items = json.loads(DEFAULT_PROMPTS_PATH.read_text(encoding="utf-8"))
+    return tuple(
+        AIPromptDefinition(
+            key=str(item["key"]),
+            label=str(item["label"]),
+            group=str(item["group"]),
+            version=str(item["version"]),
+            system_prompt=str(item.get("system_prompt") or ""),
+            prompt=str(item.get("prompt") or ""),
+        )
+        for item in raw_items
+    )
+
+
+def get_prompt_definition(task_key: str) -> AIPromptDefinition:
+    for definition in list_prompt_definitions():
+        if definition.key == task_key:
+            return definition
+    raise KeyError(task_key)
+
+
+async def _get_prompt_setting(db: AsyncSession) -> SystemSetting | None:
+    result = await db.execute(
+        select(SystemSetting).where(SystemSetting.category == AI_PROMPTS_CATEGORY)
+    )
+    return result.scalar_one_or_none()
+
+
+def _normalize_overrides(payload: dict[str, Any] | None) -> dict[str, dict[str, Any]]:
+    raw = (payload or {}).get("overrides")
+    if not isinstance(raw, dict):
+        return {}
+    return {
+        str(key): dict(value)
+        for key, value in raw.items()
+        if isinstance(value, dict)
+    }
+
+
+async def get_prompt_overrides(db: AsyncSession) -> dict[str, dict[str, Any]]:
+    if not hasattr(db, "execute"):
+        return {}
+    setting = await _get_prompt_setting(db)
+    return _normalize_overrides(setting.payload if setting else None)
+
+
+def _effective_prompt(
+    definition: AIPromptDefinition,
+    override: dict[str, Any] | None,
+) -> EffectiveAIPrompt:
+    override = override or {}
+    custom_system = override.get("system_prompt")
+    custom_prompt = override.get("prompt")
+    has_custom_system = isinstance(custom_system, str)
+    has_custom_prompt = isinstance(custom_prompt, str)
+    return EffectiveAIPrompt(
+        key=definition.key,
+        label=definition.label,
+        group=definition.group,
+        version=definition.version,
+        default_system_prompt=definition.system_prompt,
+        default_prompt=definition.prompt,
+        system_prompt=custom_system if has_custom_system else definition.system_prompt,
+        prompt=custom_prompt if has_custom_prompt else definition.prompt,
+        is_custom=has_custom_system or has_custom_prompt,
+        updated_at=str(override.get("updated_at") or "") or None,
+    )
+
+
+async def list_effective_prompts(db: AsyncSession) -> list[EffectiveAIPrompt]:
+    overrides = await get_prompt_overrides(db)
+    return [
+        _effective_prompt(definition, overrides.get(definition.key))
+        for definition in list_prompt_definitions()
+    ]
+
+
+async def get_effective_prompt(db: AsyncSession | None, task_key: str) -> EffectiveAIPrompt:
+    definition = get_prompt_definition(task_key)
+    if db is None:
+        return _effective_prompt(definition, None)
+    overrides = await get_prompt_overrides(db)
+    return _effective_prompt(definition, overrides.get(task_key))
+
+
+async def save_prompt_override(
+    db: AsyncSession,
+    task_key: str,
+    *,
+    system_prompt: str,
+    prompt: str,
+) -> EffectiveAIPrompt:
+    definition = get_prompt_definition(task_key)
+    setting = await _get_prompt_setting(db)
+    payload = dict(setting.payload or {}) if setting else {}
+    overrides = _normalize_overrides(payload)
+    overrides[definition.key] = {
+        "system_prompt": system_prompt,
+        "prompt": prompt,
+        "updated_at": datetime.now(UTC).isoformat().replace("+00:00", "Z"),
+    }
+    payload["overrides"] = overrides
+    if setting is None:
+        setting = SystemSetting(category=AI_PROMPTS_CATEGORY, payload=payload)
+        db.add(setting)
+    else:
+        setting.payload = payload
+    await db.commit()
+    return _effective_prompt(definition, overrides[definition.key])
+
+
+async def reset_prompt_override(db: AsyncSession, task_key: str) -> EffectiveAIPrompt:
+    definition = get_prompt_definition(task_key)
+    setting = await _get_prompt_setting(db)
+    if setting is None:
+        return _effective_prompt(definition, None)
+    payload = dict(setting.payload or {})
+    overrides = _normalize_overrides(payload)
+    overrides.pop(definition.key, None)
+    payload["overrides"] = overrides
+    setting.payload = payload
+    await db.commit()
+    return _effective_prompt(definition, None)
+
+
+def serialize_effective_prompt(prompt: EffectiveAIPrompt) -> dict[str, Any]:
+    return {
+        "key": prompt.key,
+        "label": prompt.label,
+        "group": prompt.group,
+        "version": prompt.version,
+        "default_system_prompt": prompt.default_system_prompt,
+        "default_prompt": prompt.default_prompt,
+        "system_prompt": prompt.system_prompt,
+        "prompt": prompt.prompt,
+        "is_custom": prompt.is_custom,
+        "updated_at": prompt.updated_at,
+    }

backend/app/api/main.py

@@ -6,16 +6,21 @@ from app.api.v1 import (
     datasource_config,
     datasources,
     docs,
+    earth,
     tasks,
     dashboard,
-    websocket,
     alerts,
     settings,
     collected_data,
+    data_products,
+    layers,
     visualization,
     vessel_aggregation,
+    vessels,
     bgp,
     news,
+    interactables,
+    realtime_sources,
     system_control,
     tv,
 )
@@ -31,17 +36,23 @@ api_router.include_router(
 api_router.include_router(datasources.router, prefix="/datasources", tags=["datasources"])
 api_router.include_router(collected_data.router, prefix="/collected", tags=["collected-data"])
 api_router.include_router(docs.router, prefix="/docs", tags=["docs"])
+api_router.include_router(earth.router, prefix="/earth", tags=["earth"])
 api_router.include_router(tasks.router, prefix="/tasks", tags=["tasks"])
 api_router.include_router(dashboard.router, prefix="/dashboard", tags=["dashboard"])
 api_router.include_router(alerts.router, prefix="/alerts", tags=["alerts"])
 api_router.include_router(settings.router, prefix="/settings", tags=["settings"])
 api_router.include_router(system_control.router, prefix="/system", tags=["system"])
+api_router.include_router(data_products.router, prefix="/data-products", tags=["data-products"])
+api_router.include_router(layers.router, prefix="/layers", tags=["layers"])
 api_router.include_router(visualization.router, prefix="/visualization", tags=["visualization"])
 api_router.include_router(
     vessel_aggregation.router,
     prefix="/vessel-aggregation",
     tags=["vessel-aggregation"],
 )
+api_router.include_router(vessels.router, prefix="/vessels", tags=["vessels"])
 api_router.include_router(bgp.router, prefix="/bgp", tags=["bgp"])
 api_router.include_router(tv.router, prefix="/tv", tags=["tv"])
 api_router.include_router(news.router, prefix="/news", tags=["news"])
+api_router.include_router(interactables.router, prefix="/interactables", tags=["interactables"])
+api_router.include_router(realtime_sources.router, prefix="/realtime-sources", tags=["realtime-sources"])

backend/app/api/v1/ai.py

@@ -3,6 +3,7 @@ from uuid import uuid4
 from fastapi import APIRouter, Depends, HTTPException, Request, Response
 from sqlalchemy.ext.asyncio import AsyncSession
 
+from app.core.logging import get_logger
 from app.core.security import get_current_user
 from app.db.session import get_db
 from app.models.user import User
@@ -47,8 +48,10 @@ from app.services.playground_chat_service import (
     stop_message,
 )
 from app.services.situational_alert_ai_brief import build_situational_alert_brief_request
+from app.services.business_logs import emit_business_log, exception_context
 
 router = APIRouter()
+logger = get_logger(__name__, service="api")
 
 
 @router.get("/provider/status", response_model=AIProviderStatusResponse)
@@ -122,6 +125,16 @@ async def create_playground_message(
     provider_client: AIProviderClient = Depends(get_ai_provider_client),
     db: AsyncSession = Depends(get_db),
 ):
+    await emit_business_log(
+        logger,
+        event="ai.playground.message.create",
+        message="Playground message creation requested",
+        category="ai",
+        service="api",
+        module=__name__,
+        user_id=current_user.id,
+        context={"session_key": payload.session_key, "preset": payload.selected_preset_key},
+    )
     return await create_turn(
         db,
         user_id=current_user.id,
@@ -136,6 +149,16 @@ async def stop_playground_message(
     current_user: User = Depends(get_current_user),
     db: AsyncSession = Depends(get_db),
 ):
+    await emit_business_log(
+        logger,
+        event="ai.playground.message.stop",
+        message="Playground message stop requested",
+        category="ai",
+        service="api",
+        module=__name__,
+        user_id=current_user.id,
+        context={"session_key": payload.session_key, "message_id": payload.message_id},
+    )
     return await stop_message(
         db,
         user_id=current_user.id,
@@ -150,6 +173,16 @@ async def resend_playground_message(
     provider_client: AIProviderClient = Depends(get_ai_provider_client),
     db: AsyncSession = Depends(get_db),
 ):
+    await emit_business_log(
+        logger,
+        event="ai.playground.message.resend",
+        message="Playground message resend requested",
+        category="ai",
+        service="api",
+        module=__name__,
+        user_id=current_user.id,
+        context={"session_key": payload.session_key, "user_message_id": payload.user_message_id},
+    )
     return await resend_turn(
         db,
         user_id=current_user.id,
@@ -214,16 +247,70 @@ async def analyze_bgp_brief(
         anomaly_limit=payload.anomaly_limit,
         collector_limit=payload.collector_limit,
     )
+    await emit_business_log(
+        logger,
+        event="ai.brief.bgp.facts_collected",
+        message="BGP brief facts collected",
+        category="ai",
+        service="api",
+        module=__name__,
+        request_id=request_id,
+        user_id=current_user.id,
+        context={
+            "incident_limit": payload.incident_limit,
+            "anomaly_limit": payload.anomaly_limit,
+            "collector_limit": payload.collector_limit,
+            "fact_count": len(facts or []),
+        },
+    )
     brief_request.preferred_model = payload.preferred_model
     brief_request.thinking = payload.thinking
 
-    analysis = await provider_client.analyze(brief_request, request_id=request_id)
-    return save_bgp_brief_record(
-        analysis,
+    await emit_business_log(
+        logger,
+        event="ai.brief.bgp.start",
+        message="BGP brief AI analysis started",
+        category="ai",
+        service="api",
+        module=__name__,
         request_id=request_id,
-        facts=facts,
-        context=context,
+        user_id=current_user.id,
+        context={"preferred_model": payload.preferred_model},
     )
+    try:
+        analysis = await provider_client.analyze(brief_request, request_id=request_id)
+        record = save_bgp_brief_record(
+            analysis,
+            request_id=request_id,
+            facts=facts,
+            context=context,
+        )
+        await emit_business_log(
+            logger,
+            event="ai.brief.bgp.completed",
+            message="BGP brief AI analysis saved",
+            category="ai",
+            service="api",
+            module=__name__,
+            request_id=request_id,
+            user_id=current_user.id,
+            context={"provider": analysis.provider, "model": analysis.model, "brief_id": record.id},
+        )
+        return record
+    except Exception as exc:
+        await emit_business_log(
+            logger,
+            event="ai.brief.bgp.failed",
+            message="BGP brief AI analysis failed",
+            category="ai",
+            level="error",
+            service="api",
+            module=__name__,
+            request_id=request_id,
+            user_id=current_user.id,
+            context=exception_context(exc, {"preferred_model": payload.preferred_model}),
+        )
+        raise
 
 
 @router.post("/alerts/brief", response_model=AlertBriefResponse)
@@ -242,17 +329,65 @@ async def analyze_alert_brief(
         db,
         alert_limit=payload.alert_limit,
     )
+    await emit_business_log(
+        logger,
+        event="ai.brief.alerts.facts_collected",
+        message="Alert brief facts collected",
+        category="ai",
+        service="api",
+        module=__name__,
+        request_id=request_id,
+        user_id=current_user.id,
+        context={"alert_limit": payload.alert_limit, "fact_count": len(facts or [])},
+    )
     brief_request.preferred_model = payload.preferred_model
     brief_request.thinking = payload.thinking
 
-    analysis = await provider_client.analyze(brief_request, request_id=request_id)
-    return AlertBriefResponse(
-        **analysis.model_dump(),
-        title=brief_request.title,
-        objective=brief_request.objective,
-        facts=facts,
-        context=context,
+    await emit_business_log(
+        logger,
+        event="ai.brief.alerts.start",
+        message="Alert brief AI analysis started",
+        category="ai",
+        service="api",
+        module=__name__,
+        request_id=request_id,
+        user_id=current_user.id,
+        context={"preferred_model": payload.preferred_model},
     )
+    try:
+        analysis = await provider_client.analyze(brief_request, request_id=request_id)
+        await emit_business_log(
+            logger,
+            event="ai.brief.alerts.completed",
+            message="Alert brief AI analysis completed",
+            category="ai",
+            service="api",
+            module=__name__,
+            request_id=request_id,
+            user_id=current_user.id,
+            context={"provider": analysis.provider, "model": analysis.model},
+        )
+        return AlertBriefResponse(
+            **analysis.model_dump(),
+            title=brief_request.title,
+            objective=brief_request.objective,
+            facts=facts,
+            context=context,
+        )
+    except Exception as exc:
+        await emit_business_log(
+            logger,
+            event="ai.brief.alerts.failed",
+            message="Alert brief AI analysis failed",
+            category="ai",
+            level="error",
+            service="api",
+            module=__name__,
+            request_id=request_id,
+            user_id=current_user.id,
+            context=exception_context(exc, {"preferred_model": payload.preferred_model}),
+        )
+        raise
 
 
 @router.post("/situational-alerts/brief", response_model=SituationalAlertBriefResponse)
@@ -268,14 +403,62 @@ async def analyze_situational_alert_brief(
     response.headers["X-Request-ID"] = request_id
 
     brief_request, facts, context = await build_situational_alert_brief_request(db)
+    await emit_business_log(
+        logger,
+        event="ai.brief.situational_alerts.facts_collected",
+        message="Situational alert brief facts collected",
+        category="ai",
+        service="api",
+        module=__name__,
+        request_id=request_id,
+        user_id=current_user.id,
+        context={"fact_count": len(facts or [])},
+    )
     brief_request.preferred_model = payload.preferred_model
     brief_request.thinking = payload.thinking
 
-    analysis = await provider_client.analyze(brief_request, request_id=request_id)
-    return SituationalAlertBriefResponse(
-        **analysis.model_dump(),
-        title=brief_request.title,
-        objective=brief_request.objective,
-        facts=facts,
-        context=context,
+    await emit_business_log(
+        logger,
+        event="ai.brief.situational_alerts.start",
+        message="Situational alert brief AI analysis started",
+        category="ai",
+        service="api",
+        module=__name__,
+        request_id=request_id,
+        user_id=current_user.id,
+        context={"preferred_model": payload.preferred_model},
     )
+    try:
+        analysis = await provider_client.analyze(brief_request, request_id=request_id)
+        await emit_business_log(
+            logger,
+            event="ai.brief.situational_alerts.completed",
+            message="Situational alert brief AI analysis completed",
+            category="ai",
+            service="api",
+            module=__name__,
+            request_id=request_id,
+            user_id=current_user.id,
+            context={"provider": analysis.provider, "model": analysis.model},
+        )
+        return SituationalAlertBriefResponse(
+            **analysis.model_dump(),
+            title=brief_request.title,
+            objective=brief_request.objective,
+            facts=facts,
+            context=context,
+        )
+    except Exception as exc:
+        await emit_business_log(
+            logger,
+            event="ai.brief.situational_alerts.failed",
+            message="Situational alert brief AI analysis failed",
+            category="ai",
+            level="error",
+            service="api",
+            module=__name__,
+            request_id=request_id,
+            user_id=current_user.id,
+            context=exception_context(exc, {"preferred_model": payload.preferred_model}),
+        )
+        raise

backend/app/api/v1/auth.py

@@ -1,26 +1,85 @@
-from datetime import timedelta
-
 from fastapi import APIRouter, Depends, HTTPException, status
 from fastapi.security import OAuth2PasswordRequestForm
 from sqlalchemy.ext.asyncio import AsyncSession
 from sqlalchemy import text
 
 from app.core.config import settings
+from app.core.logging import get_logger
 from app.core.security import (
     create_access_token,
     create_refresh_token,
-    blacklist_token,
     get_current_user,
+    get_password_hash,
     verify_password,
 )
 from app.db.session import get_db
 from app.models.user import User
 from app.schemas.token import Token
-from app.schemas.user import UserCreate, UserResponse
+from app.schemas.user import (
+    ForgotPasswordRequest,
+    ResendCodeRequest,
+    ResetPasswordRequest,
+    UserRegister,
+    UserResponse,
+    VerifyEmailRequest,
+)
+from app.services import otp
+from app.services.email import (
+    EmailError,
+    EmailNotConfiguredError,
+    send_verification_email,
+)
+
+logger = get_logger(__name__)
 
 router = APIRouter()
 
 
+def _token_response(user: User) -> dict:
+    access_token = create_access_token(data={"sub": user.id})
+    refresh = create_refresh_token(data={"sub": user.id})
+    expires_in = (
+        settings.ACCESS_TOKEN_EXPIRE_MINUTES * 60
+        if settings.ACCESS_TOKEN_EXPIRE_MINUTES > 0
+        else None
+    )
+    return {
+        "access_token": access_token,
+        "token_type": "bearer",
+        "expires_in": expires_in,
+        "refresh_token": refresh,
+        "user": {
+            "id": user.id,
+            "username": user.username,
+            "role": user.role,
+            "gatekeeper_groups": user.gatekeeper_groups or [],
+        },
+    }
+
+
+async def _load_user_by_email(db: AsyncSession, email: str) -> User | None:
+    result = await db.execute(
+        text(
+            "SELECT id, username, email, password_hash, role, is_active, gatekeeper_groups, email_verified "
+            "FROM users WHERE email = :email"
+        ),
+        {"email": email},
+    )
+    row = result.fetchone()
+    if row is None:
+        return None
+    user = User()
+    user.id = row[0]
+    user.username = row[1]
+    user.email = row[2]
+    user.password_hash = row[3]
+    user.role = row[4]
+    user.is_active = row[5]
+    user.gatekeeper_groups = row[6] or []
+    user.email_verified = bool(row[7])
+    return user
+
+
 @router.post("/login", response_model=Token)
 async def login(
     form_data: OAuth2PasswordRequestForm = Depends(),
@@ -28,7 +87,8 @@ async def login(
 ):
     result = await db.execute(
         text(
-            "SELECT id, username, email, password_hash, role, is_active, gatekeeper_groups FROM users WHERE username = :username"
+            "SELECT id, username, email, password_hash, role, is_active, gatekeeper_groups, email_verified "
+            "FROM users WHERE username = :username"
         ),
         {"username": form_data.username},
     )
@@ -47,6 +107,7 @@ async def login(
     user.role = row[4]
     user.is_active = row[5]
     user.gatekeeper_groups = row[6] or []
+    user.email_verified = bool(row[7])
 
     if not verify_password(form_data.password, user.password_hash):
         raise HTTPException(
@@ -58,25 +119,13 @@ async def login(
             status_code=status.HTTP_401_UNAUTHORIZED,
             detail="User is inactive",
         )
+    if not user.email_verified:
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail={"code": "EMAIL_NOT_VERIFIED", "email": user.email},
+        )
 
-    access_token = create_access_token(data={"sub": user.id})
-    refresh_token = create_refresh_token(data={"sub": user.id})
-
-    expires_in = None
-    if settings.ACCESS_TOKEN_EXPIRE_MINUTES > 0:
-        expires_in = settings.ACCESS_TOKEN_EXPIRE_MINUTES * 60
-
-    return {
-        "access_token": access_token,
-        "token_type": "bearer",
-        "expires_in": expires_in,
-        "user": {
-            "id": user.id,
-            "username": user.username,
-            "role": user.role,
-            "gatekeeper_groups": user.gatekeeper_groups or [],
-        },
-    }
+    return _token_response(user)
 
 
 @router.post("/refresh", response_model=Token)
@@ -116,5 +165,179 @@ async def get_me(current_user: User = Depends(get_current_user)):
         "role": current_user.role,
         "gatekeeper_groups": current_user.gatekeeper_groups or [],
         "is_active": current_user.is_active,
+        "email_verified": getattr(current_user, "email_verified", True),
         "created_at": current_user.created_at,
     }
+
+
+async def _send_code_or_raise(db: AsyncSession, email: str, code: str, purpose: str) -> None:
+    try:
+        await send_verification_email(db, to=email, code=code, purpose=purpose)
+    except EmailNotConfiguredError as exc:
+        raise HTTPException(
+            status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
+            detail={"code": exc.code, "message": str(exc)},
+        ) from exc
+    except EmailError as exc:
+        logger.warning_event(
+            "SMTP send failed",
+            event="auth.email.send_failed",
+            context={"email": email, "purpose": purpose, "error": str(exc)},
+        )
+        raise HTTPException(
+            status_code=status.HTTP_502_BAD_GATEWAY,
+            detail={"code": exc.code, "message": str(exc)},
+        ) from exc
+
+
+@router.post("/register", status_code=status.HTTP_201_CREATED)
+async def register(payload: UserRegister, db: AsyncSession = Depends(get_db)):
+    existing = await db.execute(
+        text("SELECT id, email_verified FROM users WHERE username = :u OR email = :e"),
+        {"u": payload.username, "e": payload.email},
+    )
+    row = existing.fetchone()
+    if row is not None:
+        raise HTTPException(
+            status_code=status.HTTP_409_CONFLICT,
+            detail={"code": "USER_ALREADY_EXISTS", "message": "Username or email already in use"},
+        )
+
+    user = User(
+        username=payload.username,
+        email=payload.email,
+        password_hash=get_password_hash(payload.password),
+        role="viewer",
+        is_active=True,
+        email_verified=False,
+    )
+    db.add(user)
+    await db.commit()
+
+    try:
+        code = otp.issue_code(payload.email, "register")
+    except otp.OtpResendRateLimited as exc:
+        raise HTTPException(
+            status_code=status.HTTP_429_TOO_MANY_REQUESTS,
+            detail={"code": exc.code, "retry_after_seconds": exc.retry_after_seconds},
+        ) from exc
+    await _send_code_or_raise(db, payload.email, code, "register")
+    return {"status": "pending_verification", "email": payload.email}
+
+
+@router.post("/verify-email", response_model=Token)
+async def verify_email(payload: VerifyEmailRequest, db: AsyncSession = Depends(get_db)):
+    user = await _load_user_by_email(db, payload.email)
+    if user is None:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail={"code": "USER_NOT_FOUND"},
+        )
+    try:
+        otp.verify_code(payload.email, "register", payload.code)
+    except otp.OtpExpired as exc:
+        raise HTTPException(
+            status_code=status.HTTP_410_GONE,
+            detail={"code": exc.code, "message": str(exc)},
+        ) from exc
+    except otp.OtpAttemptsExceeded as exc:
+        raise HTTPException(
+            status_code=status.HTTP_429_TOO_MANY_REQUESTS,
+            detail={"code": exc.code, "message": str(exc)},
+        ) from exc
+    except otp.OtpInvalid as exc:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail={"code": exc.code, "message": str(exc)},
+        ) from exc
+
+    await db.execute(
+        text("UPDATE users SET email_verified = TRUE WHERE id = :id"),
+        {"id": user.id},
+    )
+    await db.commit()
+    user.email_verified = True
+    return _token_response(user)
+
+
+@router.post("/resend-code")
+async def resend_code(payload: ResendCodeRequest, db: AsyncSession = Depends(get_db)):
+    user = await _load_user_by_email(db, payload.email)
+    if user is None:
+        # Avoid email enumeration; pretend success.
+        return {"status": "ok"}
+    if payload.purpose == "register" and user.email_verified:
+        raise HTTPException(
+            status_code=status.HTTP_409_CONFLICT,
+            detail={"code": "ALREADY_VERIFIED"},
+        )
+    try:
+        code = otp.issue_code(payload.email, payload.purpose)
+    except otp.OtpResendRateLimited as exc:
+        raise HTTPException(
+            status_code=status.HTTP_429_TOO_MANY_REQUESTS,
+            detail={"code": exc.code, "retry_after_seconds": exc.retry_after_seconds},
+        ) from exc
+    await _send_code_or_raise(db, payload.email, code, payload.purpose)
+    return {"status": "ok"}
+
+
+@router.post("/forgot-password")
+async def forgot_password(payload: ForgotPasswordRequest, db: AsyncSession = Depends(get_db)):
+    user = await _load_user_by_email(db, payload.email)
+    if user is None:
+        # Don't leak whether an email is registered.
+        return {"status": "ok"}
+    try:
+        code = otp.issue_code(payload.email, "reset_password")
+    except otp.OtpResendRateLimited:
+        # Silently accept; the user can retry after the cooldown.
+        return {"status": "ok"}
+    try:
+        await send_verification_email(db, to=payload.email, code=code, purpose="reset_password")
+    except EmailNotConfiguredError as exc:
+        raise HTTPException(
+            status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
+            detail={"code": exc.code, "message": str(exc)},
+        ) from exc
+    except EmailError as exc:
+        logger.warning_event(
+            "SMTP send failed",
+            event="auth.email.send_failed",
+            context={"email": payload.email, "purpose": "reset_password", "error": str(exc)},
+        )
+    return {"status": "ok"}
+
+
+@router.post("/reset-password")
+async def reset_password(payload: ResetPasswordRequest, db: AsyncSession = Depends(get_db)):
+    user = await _load_user_by_email(db, payload.email)
+    if user is None:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail={"code": "OTP_INVALID"},
+        )
+    try:
+        otp.verify_code(payload.email, "reset_password", payload.code)
+    except otp.OtpExpired as exc:
+        raise HTTPException(
+            status_code=status.HTTP_410_GONE,
+            detail={"code": exc.code, "message": str(exc)},
+        ) from exc
+    except otp.OtpAttemptsExceeded as exc:
+        raise HTTPException(
+            status_code=status.HTTP_429_TOO_MANY_REQUESTS,
+            detail={"code": exc.code, "message": str(exc)},
+        ) from exc
+    except otp.OtpInvalid as exc:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail={"code": exc.code, "message": str(exc)},
+        ) from exc
+
+    await db.execute(
+        text("UPDATE users SET password_hash = :p, email_verified = TRUE WHERE id = :id"),
+        {"p": get_password_hash(payload.new_password), "id": user.id},
+    )
+    await db.commit()
+    return {"status": "ok"}

backend/app/api/v1/bgp.py

@@ -14,10 +14,17 @@ from app.models.bgp_incident import BGPIncident
 from app.models.bgp_observation import BGPObservation
 from app.models.user import User
 from app.services.bgp_collector_locations import (
+    build_bgp_collector_location_query,
     collect_bgp_collector_location_candidates,
     get_bgp_collector_location_dict,
 )
 from app.services.bgp_collectors import build_bgp_collector_coverage
+from app.services.ai_client import get_ai_provider_client
+from app.api.v1.settings import get_web_search_client
+from app.services.location.llm_fallback import (
+    collect_llm_location_fallback_candidate,
+    collect_location_search_evidence,
+)
 
 router = APIRouter()
 
@@ -282,6 +289,7 @@ async def collect_bgp_collector_location(
     collector_id: str,
     payload: CollectBGPCollectorLocationRequest,
     current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
 ):
     """Run the shared location pipeline for a BGP route collector.
 
@@ -307,6 +315,47 @@ async def collect_bgp_collector_location(
         country=country,
         operator=operator,
     )
+    llm_failure_reason = None
+    if not candidates:
+        query = build_bgp_collector_location_query(
+            collector=collector_id,
+            site=site,
+            city=city,
+            country=country,
+            operator=operator,
+        )
+        llm_result = None
+        try:
+            web_search_client = await get_web_search_client(db)
+            search_result = await collect_location_search_evidence(
+                web_search_client=web_search_client,
+                query=query,
+                entity_type="bgp_collector",
+            )
+            attempted_queries = [*attempted_queries, *search_result.attempted_queries]
+            if not search_result.evidence:
+                llm_failure_reason = search_result.failure_reason
+                raise RuntimeError(search_result.failure_reason or "no WebSearch evidence")
+            provider_client = await get_ai_provider_client(db)
+            llm_result = await collect_llm_location_fallback_candidate(
+                provider_client=provider_client,
+                query=query,
+                entity_type="bgp_collector",
+                db=db,
+                attempted_queries=attempted_queries,
+                search_evidence=search_result.evidence,
+            )
+        except Exception as exc:
+            if llm_failure_reason is None:
+                llm_failure_reason = f"LLM location factcheck unavailable: {exc}"
+                attempted_queries = [
+                    *attempted_queries,
+                    f"llm_factcheck:bgp_collector:{collector_id or 'unknown'}",
+                ]
+        if llm_result is not None:
+            attempted_queries = [*attempted_queries, *llm_result.attempted_queries]
+            candidates = llm_result.candidates
+            llm_failure_reason = llm_result.failure_reason
 
     context = {
         "collector": collector_id,
@@ -327,6 +376,7 @@ async def collect_bgp_collector_location(
             ),
             "candidates": [],
             "attempted_queries": list(attempted_queries),
+            "llm_failure_reason": llm_failure_reason,
             "context": context,
         }
 

backend/app/api/v1/collected_data.py

@@ -102,7 +102,12 @@ def build_search_rank_sql(search: Optional[str]) -> str:
     """
 
 
-def serialize_collected_row(row, source_name_map: dict[str, str] | None = None) -> dict:
+def serialize_collected_row(
+    row,
+    source_name_map: dict[str, str] | None = None,
+    *,
+    include_metadata: bool = True,
+) -> dict:
     metadata = row[7]
     source = row[1]
     return {
@@ -120,7 +125,7 @@ def serialize_collected_row(row, source_name_map: dict[str, str] | None = None)
         "longitude": get_metadata_field(metadata, "longitude"),
         "value": get_metadata_field(metadata, "value"),
         "unit": get_metadata_field(metadata, "unit"),
-        "metadata": metadata,
+        "metadata": metadata if include_metadata else None,
         "cores": get_metadata_field(metadata, "cores"),
         "rmax": get_metadata_field(metadata, "rmax"),
         "rpeak": get_metadata_field(metadata, "rpeak"),
@@ -145,6 +150,7 @@ async def list_collected_data(
     search: Optional[str] = Query(None, description="搜索名称"),
     page: int = Query(1, ge=1, description="页码"),
     page_size: int = Query(20, ge=1, le=100, description="每页数量"),
+    include_metadata: bool = Query(True, description="是否返回完整 metadata 字段"),
     current_user: User = Depends(get_current_user),
     db: AsyncSession = Depends(get_db),
 ):
@@ -201,7 +207,7 @@ async def list_collected_data(
 
     data = []
     for row in rows:
-        data.append(serialize_collected_row(row[:11], source_name_map))
+        data.append(serialize_collected_row(row[:11], source_name_map, include_metadata=include_metadata))
 
     return {
         "total": total,

backend/app/api/v1/data_products.py

@@ -0,0 +1,98 @@
+from datetime import UTC, datetime
+
+from fastapi import APIRouter, Depends, HTTPException
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.api.v1.visualization import get_visualization_geo_summary
+from app.core.time import to_iso8601_utc
+from app.db.session import get_db
+
+router = APIRouter()
+
+PRODUCT_DEFINITIONS: dict[str, dict] = {
+    "vessels": {
+        "name": "船只",
+        "sources": ["aisstream_vessels", "barentswatch_vessels"],
+        "primary_stat_key": "vessel_count",
+        "stat_keys": ["vessel_count", "vessel_raw_unique_mmsi", "vessel_legacy_unique_mmsi"],
+    },
+    "cables": {
+        "name": "海底光缆",
+        "sources": [
+            "arcgis_cables",
+            "arcgis_landing_points",
+            "arcgis_cable_landing_relation",
+            "telegeography_cables",
+            "telegeography_landing",
+            "telegeography_systems",
+            "fao_landing_points",
+        ],
+        "primary_stat_key": "cable_count",
+        "stat_keys": ["cable_count", "landing_point_count"],
+    },
+    "satellites": {
+        "name": "卫星",
+        "sources": ["celestrak_tle", "spacetrack_tle"],
+        "primary_stat_key": "satellite_count",
+        "stat_keys": ["satellite_count"],
+    },
+    "bgp": {
+        "name": "BGP",
+        "sources": [
+            "ris_live_bgp",
+            "bgpstream_bgp",
+            "iptoasn_prefix_geo",
+            "opengeofeed_prefix_geo",
+            "nro_delegated_prefix_geo",
+        ],
+        "primary_stat_key": "bgp_event_count",
+        "stat_keys": ["bgp_event_count", "bgp_incident_count", "bgp_anomaly_count", "bgp_collector_count"],
+    },
+    "compute": {
+        "name": "算力",
+        "sources": ["top500", "epoch_ai_gpu"],
+        "primary_stat_key": "compute_center_count",
+        "stat_keys": ["compute_center_count", "supercomputer_count", "gpu_cluster_count"],
+    },
+}
+
+
+def _build_product_status(product_id: str, summary: dict) -> dict:
+    definition = PRODUCT_DEFINITIONS[product_id]
+    stats = summary.get("stats", {})
+    product_stats = {key: stats.get(key, 0) for key in definition["stat_keys"]}
+    total_count = int(product_stats.get(definition["primary_stat_key"]) or 0)
+    return {
+        "product_id": product_id,
+        "name": definition["name"],
+        "sources": definition["sources"],
+        "generated_at": summary.get("generated_at") or to_iso8601_utc(datetime.now(UTC)),
+        "total_count": total_count,
+        "stats": product_stats,
+        "build_state": "ready",
+        "stats_scope": "global",
+        "stats_freshness": "cached_or_indexed",
+    }
+
+
+@router.get("")
+async def list_data_products(db: AsyncSession = Depends(get_db)):
+    summary = await get_visualization_geo_summary(db)
+    return {
+        "generated_at": summary.get("generated_at"),
+        "data": [
+            _build_product_status(product_id, summary)
+            for product_id in PRODUCT_DEFINITIONS
+        ],
+    }
+
+
+@router.get("/{product_id}/status")
+async def get_data_product_status(
+    product_id: str,
+    db: AsyncSession = Depends(get_db),
+):
+    if product_id not in PRODUCT_DEFINITIONS:
+        raise HTTPException(status_code=404, detail="Unknown data product")
+    summary = await get_visualization_geo_summary(db)
+    return _build_product_status(product_id, summary)

backend/app/api/v1/datasource_config.py

@@ -5,7 +5,7 @@ from datetime import datetime
 import base64
 import json
 import re
-from fastapi import APIRouter, Depends, HTTPException, Query
+from fastapi import APIRouter, Depends, HTTPException, Query, Request, status
 from sqlalchemy import delete, select, func
 from sqlalchemy.ext.asyncio import AsyncSession
 from pydantic import BaseModel, Field
@@ -22,6 +22,7 @@ from app.models.vessel import AISRawObservation, AISSourceHealth
 from app.core.security import get_current_user
 from app.core.cache import cache
 from app.core.time import to_iso8601_utc
+from app.ai_tasks.prompts import get_effective_prompt
 from app.schemas.ai import SituationalAnalysisRequest
 from app.services.ai_client import AIProviderClient, get_ai_provider_client
 from app.services.datasource_mapping import (
@@ -41,15 +42,82 @@ from app.services.custom_datasource_runtime import (
     stop_custom_stream,
     test_websocket_config,
 )
+
+DATASOURCE_MAPPING_PROMPT_KEY = "datasource.mapping"
 from app.services.datasource_connectivity import (
+    _resolve_aisstream_api_key,
+    _resolve_spacetrack_credentials_with_override,
     get_builtin_connection_status,
     save_connectivity_success,
     strip_connectivity_validation,
     test_builtin_connectivity,
 )
+from app.services.barentswatch import resolve_barentswatch_config
+from app.services.persistent_logs import record_audit_log
 
 router = APIRouter()
 
+SECRET_REVEAL_ROLES = {"admin", "super_admin"}
+
+
+def _user_role_value(user: User) -> str:
+    role = getattr(user, "role", "")
+    return str(getattr(role, "value", role) or "").lower()
+
+
+def _user_display_name(user: User) -> str:
+    return str(getattr(user, "username", None) or getattr(user, "email", None) or getattr(user, "id", ""))
+
+
+async def _record_datasource_secret_reveal(
+    *,
+    current_user: User,
+    request: Request,
+    target_id: str,
+    result: str,
+    details: dict[str, Any],
+) -> None:
+    await record_audit_log(
+        action="datasource_config.secret.reveal",
+        actor_id=getattr(current_user, "id", None),
+        actor_name=_user_display_name(current_user),
+        target_type="datasource_config_secret",
+        target_id=target_id,
+        result=result,
+        ip=request.client.host if request.client else None,
+        details=details,
+    )
+
+
+async def _ensure_datasource_secret_reveal_allowed(
+    current_user: User,
+    request: Request,
+    target_id: str,
+    details: dict[str, Any],
+) -> None:
+    if _user_role_value(current_user) in SECRET_REVEAL_ROLES:
+        return
+    await _record_datasource_secret_reveal(
+        current_user=current_user,
+        request=request,
+        target_id=target_id,
+        result="denied",
+        details={**details, "role": _user_role_value(current_user)},
+    )
+    raise HTTPException(
+        status_code=status.HTTP_403_FORBIDDEN,
+        detail="Only administrators can reveal datasource credentials",
+    )
+
+def _default_builtin_config(name: str) -> dict[str, Any]:
+    return {"timeout": 30, "retry": 3}
+
+
+def _default_builtin_source_type(name: str) -> str:
+    if name == "aisstream_vessels":
+        return "websocket"
+    return "http"
+
 
 class DataSourceConfigCreate(BaseModel):
     name: str = Field(..., min_length=1, max_length=100)
@@ -364,7 +432,7 @@ async def list_all_datasources(
     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
+    from app.core.data_sources import get_data_sources_config
 
     config = get_data_sources_config()
 
@@ -372,38 +440,144 @@ async def list_all_datasources(
     db_configs = {c.name: c for c in db_query.scalars().all()}
 
     result = []
-    for name, yaml_key in COLLECTOR_URL_KEYS.items():
+    for name, metadata in DEFAULT_DATASOURCES.items():
         yaml_url = config.get_yaml_url(name)
         db_config = db_configs.get(name)
+        default_config = _default_builtin_config(name)
+        default_url = yaml_url
+        db_auth_config = db_config.auth_config or {} if db_config else {}
 
         result.append(
             {
                 "name": name,
-                "default_url": yaml_url,
-                "endpoint": db_config.endpoint if db_config else yaml_url,
+                "requires_credentials": bool(metadata.get("requires_credentials", False)),
+                "credential_provider": metadata.get("credential_provider"),
+                "credential_status": metadata.get("credential_status", "none"),
+                "default_url": default_url,
+                "endpoint": db_config.endpoint if db_config else default_url,
                 "is_overridden": db_config is not None and db_config.endpoint != yaml_url
-                if yaml_url
+                if default_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",
+                "source_type": db_config.source_type if db_config else _default_builtin_source_type(name),
                 "auth_type": db_config.auth_type if db_config else "none",
+                "auth_config": {
+                    "client_id": db_auth_config.get("client_id") or "",
+                    "username": db_auth_config.get("username") or "",
+                    "key_name": db_auth_config.get("key_name") or db_auth_config.get("param_name") or "",
+                    "param_name": db_auth_config.get("param_name") or db_auth_config.get("key_name") or "",
+                    "location": db_auth_config.get("location") or db_auth_config.get("in") or "",
+                    "in": db_auth_config.get("in") or db_auth_config.get("location") or "",
+                },
                 "auth_configured": {
-                    "api_key": bool((db_config.auth_config or {}).get("api_key"))
-                    if db_config
-                    else False,
+                    "api_key": bool(db_auth_config.get("api_key")),
+                    "client_id": bool(db_auth_config.get("client_id")),
+                    "client_secret": bool(db_auth_config.get("client_secret")),
+                    "username": bool(db_auth_config.get("username")),
+                    "password": bool(db_auth_config.get("password")),
                 },
                 "headers": db_config.headers if db_config else {},
-                "config": strip_connectivity_validation(db_config.config if db_config else {}),
+                "config": strip_connectivity_validation(db_config.config if db_config else default_config),
                 "config_id": db_config.id if db_config else None,
                 "description": db_config.description
                 if db_config
-                else f"Data source from YAML: {yaml_key}",
+                else f"内置采集器默认配置：{metadata.get('display_name') or metadata.get('name') or name}",
             }
         )
 
     return {"total": len(result), "data": result}
 
 
+@router.get("/configs/secrets")
+async def reveal_builtin_config_secrets(
+    request: Request,
+    name: str = Query(..., min_length=1),
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    """Reveal configured built-in datasource credentials for admin editing."""
+    source = name.strip()
+    metadata = DEFAULT_DATASOURCES.get(source)
+    if not metadata or not metadata.get("requires_credentials"):
+        raise HTTPException(status_code=404, detail="Credentialed datasource config not found")
+
+    provider = str(metadata.get("credential_provider") or "")
+    target_id = f"datasource_config:{source}"
+    await _ensure_datasource_secret_reveal_allowed(
+        current_user,
+        request,
+        target_id,
+        {"source": source, "provider": provider},
+    )
+
+    result = await db.execute(select(DataSourceConfig).where(DataSourceConfig.name == source))
+    record = result.scalar_one_or_none()
+    auth_config = dict(record.auth_config or {}) if record else {}
+    payload: dict[str, Any] = {
+        "name": source,
+        "provider": provider,
+    }
+    details: dict[str, Any] = {"source": source, "provider": provider}
+
+    if provider == "barentswatch":
+        resolved = await resolve_barentswatch_config(db)
+        client_id = str(auth_config.get("client_id") or resolved.client_id or "")
+        client_secret = str(auth_config.get("client_secret") or resolved.client_secret or "")
+        source_label = "datasource_config" if auth_config.get("client_id") or auth_config.get("client_secret") else resolved.credential_source
+        payload.update(
+            {
+                "client_id": client_id,
+                "client_secret": client_secret,
+                "client_id_source": source_label if client_id else "missing",
+                "client_secret_source": source_label if client_secret else "missing",
+            }
+        )
+        details.update(
+            {
+                "client_id_configured": bool(client_id),
+                "client_secret_configured": bool(client_secret),
+                "credential_source": source_label,
+            }
+        )
+    elif provider == "aisstream":
+        api_key, api_key_source = await _resolve_aisstream_api_key(db)
+        payload.update({"api_key": api_key, "api_key_source": api_key_source})
+        details.update({"api_key_configured": bool(api_key), "api_key_source": api_key_source})
+    elif provider == "spacetrack":
+        if auth_config.get("username") or auth_config.get("password"):
+            username = str(auth_config.get("username") or "")
+            password = str(auth_config.get("password") or "")
+            credential_source = "datasource_config"
+        else:
+            username, password, credential_source = _resolve_spacetrack_credentials_with_override()
+        payload.update(
+            {
+                "username": username,
+                "password": password,
+                "username_source": credential_source if username else "missing",
+                "password_source": credential_source if password else "missing",
+            }
+        )
+        details.update(
+            {
+                "username_configured": bool(username),
+                "password_configured": bool(password),
+                "credential_source": credential_source,
+            }
+        )
+    else:
+        raise HTTPException(status_code=400, detail="Datasource credential provider is not supported")
+
+    await _record_datasource_secret_reveal(
+        current_user=current_user,
+        request=request,
+        target_id=target_id,
+        result="success",
+        details=details,
+    )
+    return payload
+
+
 @router.get("/configs/{config_id}")
 async def get_config(
     config_id: int,
@@ -757,14 +931,12 @@ async def propose_datasource_mapping(
     generated_by = "heuristic"
     if payload.use_ai:
         try:
+            prompt = await get_effective_prompt(db, DATASOURCE_MAPPING_PROMPT_KEY)
             response = await ai_client.analyze(
                 SituationalAnalysisRequest(
                     title=f"Generate datasource mapping for {schema.key}",
-                    objective=(
-                        "Return only JSON for a deterministic mapping DSL. "
-                        "The JSON must contain source.items_path and fields. "
-                        "Do not include prose or code."
-                    ),
+                    objective=prompt.prompt,
+                    system_prompt=prompt.system_prompt or None,
                     context={
                         "target_schema": schema.to_dict(),
                         "sample_payload": redacted_sample,

backend/app/api/v1/earth.py

@@ -0,0 +1,441 @@
+"""Earth asset management APIs."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+from uuid import uuid4
+
+from fastapi import APIRouter, Depends, File, HTTPException, Request, UploadFile, status
+from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
+from pydantic import BaseModel, Field
+from sqlalchemy import delete, func, select, text
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.core.config import settings as app_settings
+from app.core.security import decode_token, get_current_user, redis_client
+from app.db.session import get_db
+from app.models.collected_data import CollectedData
+from app.models.datasource import DataSource
+from app.models.datasource_config import DataSourceConfig
+from app.models.system_setting import SystemSetting
+from app.models.user import User
+from app.services.tv_streams import get_tv_settings_payload
+from app.services.earth_boundaries import (
+    EarthBoundaryBuildError,
+    get_boundary_build_status,
+    get_boundary_status,
+    save_boundary_config,
+    start_boundary_build_job,
+)
+
+
+router = APIRouter()
+optional_bearer = HTTPBearer(auto_error=False)
+REPO_ROOT = Path(__file__).resolve().parents[4]
+EARTH_BRAND_ASSET_DIR = REPO_ROOT / "data" / "earth-brand"
+EARTH_BRAND_ASSET_URL_PREFIX = "/earth-brand-assets"
+EARTH_BRAND_CATEGORY = "earth_brand"
+EARTH_ABOUT_CATEGORY = "earth_about"
+SYSTEM_SETTINGS_CATEGORY = "system"
+MAX_EARTH_BRAND_ASSET_BYTES = 3 * 1024 * 1024
+ALLOWED_EARTH_BRAND_EXTENSIONS = {".png", ".jpg", ".jpeg", ".webp", ".svg"}
+
+
+def _app_version_label() -> str:
+    version = str(app_settings.VERSION or "").strip() or "0.0.0"
+    return version if version.startswith("v") else f"v{version}"
+
+
+DEFAULT_EARTH_BRAND = {
+    "logo_src": "/earth/assets/brand/earth-logo.png",
+    "title_src": "/earth/assets/brand/title-zh.png",
+    "title_text": "智能星球计划",
+    "subtitle": "现实层宇宙全息感知系统",
+    "description": "卫星 · 海底光缆 · 算力基础设施",
+    "aria_label": "智能星球计划品牌标识",
+    "title_alt": "智能星球计划",
+}
+
+DEFAULT_EARTH_ABOUT = {
+    "logo_src": "/earth/assets/brand/lim-logo.png",
+    "kicker": "About",
+    "title": "智能星球计划",
+    "version": _app_version_label(),
+    "description": "面向临空场景下的智能媒体研究、全球态势感知与多源开放数据巡航，提供可视化观测、事件聚合与交互式探索能力。",
+    "meta": [
+        {"label": "出品方", "value": "浙江大学临空智能媒体研究院"},
+        {"label": "策划人", "value": "方兴东、黄柳青"},
+        {"label": "产品兼开发者", "value": "钱坤、张鸽、齐鹏"},
+    ],
+}
+EARTH_ABOUT_LEGACY_PLANNER_VALUE = "黄柳青"
+
+
+class EarthBoundaryConfigPayload(BaseModel):
+    config: dict[str, Any] = Field(default_factory=dict)
+
+
+class EarthBrandPayload(BaseModel):
+    logo_src: str = Field(default=DEFAULT_EARTH_BRAND["logo_src"], max_length=1000)
+    title_src: str = Field(default=DEFAULT_EARTH_BRAND["title_src"], max_length=1000)
+    title_text: str = Field(default=DEFAULT_EARTH_BRAND["title_text"], max_length=120)
+    subtitle: str = Field(default=DEFAULT_EARTH_BRAND["subtitle"], max_length=160)
+    description: str = Field(default=DEFAULT_EARTH_BRAND["description"], max_length=200)
+    aria_label: str = Field(default=DEFAULT_EARTH_BRAND["aria_label"], max_length=200)
+    title_alt: str = Field(default=DEFAULT_EARTH_BRAND["title_alt"], max_length=200)
+
+
+class EarthAboutMetaItem(BaseModel):
+    label: str = Field(default="", max_length=80)
+    value: str = Field(default="", max_length=240)
+
+
+class EarthAboutPayload(BaseModel):
+    logo_src: str = Field(default=DEFAULT_EARTH_ABOUT["logo_src"], max_length=1000)
+    kicker: str = Field(default=DEFAULT_EARTH_ABOUT["kicker"], max_length=80)
+    title: str = Field(default=DEFAULT_EARTH_ABOUT["title"], max_length=160)
+    version: str = Field(default=DEFAULT_EARTH_ABOUT["version"], max_length=80)
+    description: str = Field(default=DEFAULT_EARTH_ABOUT["description"], max_length=800)
+    meta: list[EarthAboutMetaItem] = Field(default_factory=list)
+
+
+def _normalize_earth_brand_payload(payload: dict[str, Any] | None) -> dict[str, str]:
+    merged = DEFAULT_EARTH_BRAND.copy()
+    if payload:
+        for key in DEFAULT_EARTH_BRAND:
+            value = payload.get(key)
+            if value is not None:
+                merged[key] = str(value).strip()
+
+    if not merged["title_text"]:
+        merged["title_text"] = DEFAULT_EARTH_BRAND["title_text"]
+    if not merged["aria_label"]:
+        merged["aria_label"] = merged["title_text"]
+    if not merged["title_alt"]:
+        merged["title_alt"] = merged["title_text"]
+    return merged
+
+
+def _normalize_earth_about_payload(payload: dict[str, Any] | None) -> dict[str, Any]:
+    merged: dict[str, Any] = {
+        key: value
+        for key, value in DEFAULT_EARTH_ABOUT.items()
+        if key != "meta"
+    }
+    raw_meta = DEFAULT_EARTH_ABOUT["meta"]
+    if payload:
+        for key in ("logo_src", "kicker", "title", "description"):
+            value = payload.get(key)
+            if value is not None:
+                merged[key] = str(value).strip()
+        raw_meta = payload.get("meta") if isinstance(payload.get("meta"), list) else raw_meta
+    merged["version"] = _app_version_label()
+
+    for key, default_value in DEFAULT_EARTH_ABOUT.items():
+        if key == "meta":
+            continue
+        if not merged.get(key):
+            merged[key] = default_value
+
+    normalized_meta: list[dict[str, str]] = []
+    for item in raw_meta:
+        if not isinstance(item, dict):
+            continue
+        label = str(item.get("label") or "").strip()
+        value = str(item.get("value") or "").strip()
+        if label == "策划人" and value == EARTH_ABOUT_LEGACY_PLANNER_VALUE:
+            value = "方兴东、黄柳青"
+        if label or value:
+            normalized_meta.append({"label": label, "value": value})
+    if not normalized_meta:
+        normalized_meta = [dict(item) for item in DEFAULT_EARTH_ABOUT["meta"]]
+    merged["meta"] = normalized_meta
+    return merged
+
+
+def _is_demo_mode_enabled(payload: Any) -> bool:
+    return bool(payload.get("demo_mode")) if isinstance(payload, dict) else False
+
+
+async def _get_earth_brand_record(db: AsyncSession) -> SystemSetting | None:
+    result = await db.execute(
+        select(SystemSetting).where(SystemSetting.category == EARTH_BRAND_CATEGORY)
+    )
+    return result.scalar_one_or_none()
+
+
+async def _get_earth_brand_payload(db: AsyncSession) -> dict[str, Any]:
+    record = await _get_earth_brand_record(db)
+    return {
+        "brand": _normalize_earth_brand_payload(record.payload if record else None),
+        "is_default": record is None,
+    }
+
+
+async def _get_earth_about_record(db: AsyncSession) -> SystemSetting | None:
+    result = await db.execute(
+        select(SystemSetting).where(SystemSetting.category == EARTH_ABOUT_CATEGORY)
+    )
+    return result.scalar_one_or_none()
+
+
+async def _get_earth_about_payload(db: AsyncSession) -> dict[str, Any]:
+    record = await _get_earth_about_record(db)
+    return {
+        "about": _normalize_earth_about_payload(record.payload if record else None),
+        "is_default": record is None,
+    }
+
+
+async def _get_optional_current_user(
+    credentials: HTTPAuthorizationCredentials | None = Depends(optional_bearer),
+    db: AsyncSession = Depends(get_db),
+) -> User | None:
+    if credentials is None:
+        return None
+    token = credentials.credentials
+    if redis_client.sismember("blacklisted_tokens", token):
+        return None
+    payload = decode_token(token)
+    if payload is None or payload.get("type") != "access":
+        return None
+    user_id = payload.get("sub")
+    if user_id is None:
+        return None
+    result = await db.execute(
+        text(
+            "SELECT id, username, email, password_hash, role, is_active, gatekeeper_groups FROM users WHERE id = :id"
+        ),
+        {"id": int(user_id)},
+    )
+    row = result.fetchone()
+    if row is None or not row[5]:
+        return None
+    user = User()
+    user.id = row[0]
+    user.username = row[1]
+    user.email = row[2]
+    user.password_hash = row[3]
+    user.role = row[4]
+    user.is_active = row[5]
+    user.gatekeeper_groups = row[6] or []
+    return user
+
+
+@router.get("/brand")
+async def get_earth_brand(db: AsyncSession = Depends(get_db)):
+    return await _get_earth_brand_payload(db)
+
+
+@router.put("/brand")
+async def update_earth_brand(
+    payload: EarthBrandPayload,
+    _current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    normalized = _normalize_earth_brand_payload(payload.model_dump())
+    record = await _get_earth_brand_record(db)
+    if record is None:
+        record = SystemSetting(category=EARTH_BRAND_CATEGORY, payload=normalized)
+        db.add(record)
+    else:
+        record.payload = normalized
+    await db.commit()
+    await db.refresh(record)
+    return {"status": "updated", "brand": _normalize_earth_brand_payload(record.payload), "is_default": False}
+
+
+@router.delete("/brand")
+@router.post("/brand/reset")
+async def reset_earth_brand(
+    _current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    await db.execute(delete(SystemSetting).where(SystemSetting.category == EARTH_BRAND_CATEGORY))
+    await db.commit()
+    return {"status": "reset", "brand": DEFAULT_EARTH_BRAND.copy(), "is_default": True}
+
+
+@router.post("/brand/assets")
+async def upload_earth_brand_asset(
+    file: UploadFile = File(...),
+    _current_user: User = Depends(get_current_user),
+):
+    original_name = file.filename or ""
+    extension = Path(original_name).suffix.lower()
+    if extension not in ALLOWED_EARTH_BRAND_EXTENSIONS:
+        raise HTTPException(
+            status_code=400,
+            detail={
+                "code": "unsupported_file_type",
+                "message": "Only png, jpg, jpeg, webp, and svg brand assets are supported.",
+            },
+        )
+
+    content = await file.read(MAX_EARTH_BRAND_ASSET_BYTES + 1)
+    if len(content) > MAX_EARTH_BRAND_ASSET_BYTES:
+        raise HTTPException(
+            status_code=400,
+            detail={
+                "code": "file_too_large",
+                "message": "Brand asset must be 3 MB or smaller.",
+            },
+        )
+
+    EARTH_BRAND_ASSET_DIR.mkdir(parents=True, exist_ok=True)
+    safe_name = f"{uuid4().hex}{extension}"
+    destination = EARTH_BRAND_ASSET_DIR / safe_name
+    destination.write_bytes(content)
+    asset_url = f"{EARTH_BRAND_ASSET_URL_PREFIX}/{safe_name}"
+    return {"url": asset_url, "filename": safe_name, "content_type": file.content_type}
+
+
+@router.get("/about")
+async def get_earth_about(db: AsyncSession = Depends(get_db)):
+    return await _get_earth_about_payload(db)
+
+
+@router.put("/about")
+async def update_earth_about(
+    payload: EarthAboutPayload,
+    _current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    normalized = _normalize_earth_about_payload(payload.model_dump())
+    record = await _get_earth_about_record(db)
+    if record is None:
+        record = SystemSetting(category=EARTH_ABOUT_CATEGORY, payload=normalized)
+        db.add(record)
+    else:
+        record.payload = normalized
+    await db.commit()
+    await db.refresh(record)
+    return {"status": "updated", "about": _normalize_earth_about_payload(record.payload), "is_default": False}
+
+
+@router.delete("/about")
+async def reset_earth_about(
+    _current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    await db.execute(delete(SystemSetting).where(SystemSetting.category == EARTH_ABOUT_CATEGORY))
+    await db.commit()
+    return {"status": "reset", "about": _normalize_earth_about_payload(None), "is_default": True}
+
+
+@router.get("/oobe-status")
+async def get_earth_oobe_status(
+    current_user: User | None = Depends(_get_optional_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    current_count_result = await db.execute(
+        select(func.count(CollectedData.id)).where(CollectedData.is_current.is_(True))
+    )
+    current_record_count = int(current_count_result.scalar() or 0)
+    system_result = await db.execute(
+        select(SystemSetting).where(SystemSetting.category == SYSTEM_SETTINGS_CATEGORY)
+    )
+    system_record = system_result.scalar_one_or_none()
+    demo_mode = _is_demo_mode_enabled(system_record.payload if system_record else None)
+
+    datasource_count_result = await db.execute(select(func.count(DataSource.id)))
+    datasource_count = int(datasource_count_result.scalar() or 0)
+    active_datasource_count_result = await db.execute(
+        select(func.count(DataSource.id)).where(DataSource.is_active.is_(True))
+    )
+    active_datasource_count = int(active_datasource_count_result.scalar() or 0)
+    config_result = await db.execute(select(func.count(DataSourceConfig.id)))
+    custom_config_count = int(config_result.scalar() or 0)
+
+    tv_payload = await get_tv_settings_payload(db)
+    tv_sources = tv_payload.get("sources") if isinstance(tv_payload, dict) else []
+    tv_source_count = len(tv_sources) if isinstance(tv_sources, list) else 0
+
+    boundary_status = get_boundary_status()
+    has_core_layers = bool(boundary_status.get("ready") or boundary_status.get("available") or boundary_status.get("status") in {"ready", "built", "ok"})
+    has_collected_data = current_record_count > 0
+    ready = has_collected_data
+
+    suggestions: list[str] = []
+    if demo_mode:
+        suggestions.append("演示模式已开启")
+    if not current_user:
+        suggestions.append("登录控制台")
+    if not has_collected_data:
+        suggestions.append("触发数据源采集")
+    if not custom_config_count:
+        suggestions.append("确认采集器配置")
+    if not has_core_layers:
+        suggestions.append("构建或启用 Earth 图层")
+
+    return {
+        "ready": ready,
+        "demo_mode": demo_mode,
+        "authenticated": current_user is not None,
+        "needs_login": current_user is None and not ready and not demo_mode,
+        "has_collected_data": has_collected_data,
+        "has_tv_sources": tv_source_count > 0,
+        "has_core_layers": has_core_layers,
+        "current_record_count": current_record_count,
+        "datasource_count": datasource_count,
+        "active_datasource_count": active_datasource_count,
+        "custom_config_count": custom_config_count,
+        "tv_source_count": tv_source_count,
+        "suggestions": suggestions,
+        "login_url": "/login?next=/datasources",
+        "datasources_url": "/datasources",
+        "collection_url": "/collection-management",
+    }
+
+
+@router.get("/boundaries/status")
+async def get_earth_boundary_status():
+    return get_boundary_status()
+
+def _is_loopback_request(request: Request) -> bool:
+    host = request.client.host if request.client else ""
+    return host in {"127.0.0.1", "::1", "localhost"} or host.startswith("127.")
+
+
+def _require_local_or_user(request: Request, user: User | None) -> None:
+    if user is not None or _is_loopback_request(request):
+        return
+    raise HTTPException(
+        status_code=status.HTTP_401_UNAUTHORIZED,
+        detail="Authentication required outside localhost",
+    )
+
+
+@router.put("/boundaries/config")
+async def update_earth_boundary_config(
+    payload: EarthBoundaryConfigPayload,
+    _current_user: User = Depends(get_current_user),
+):
+    try:
+        return save_boundary_config(payload.config)
+    except EarthBoundaryBuildError as exc:
+        raise HTTPException(
+            status_code=400,
+            detail={"code": exc.code, "message": str(exc), "details": exc.details},
+        ) from exc
+
+
+@router.post("/boundaries/build")
+async def build_earth_boundary_assets(
+    request: Request,
+    current_user: User | None = Depends(_get_optional_current_user),
+):
+    _require_local_or_user(request, current_user)
+    try:
+        return await start_boundary_build_job()
+    except EarthBoundaryBuildError as exc:
+        raise HTTPException(
+            status_code=400,
+            detail={"code": exc.code, "message": str(exc), "details": exc.details},
+        ) from exc
+
+
+@router.get("/boundaries/build/status")
+async def get_earth_boundary_build_status():
+    return get_boundary_build_status()

backend/app/api/v1/interactables.py

@@ -0,0 +1,190 @@
+"""CRUD APIs for persistent Earth interactables."""
+
+from __future__ import annotations
+
+from datetime import UTC, datetime
+from typing import Any
+
+from fastapi import APIRouter, Depends, HTTPException, Query, Response, status
+from pydantic import BaseModel, Field, field_validator
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.core.security import get_current_user
+from app.db.session import get_db
+from app.models.earth_interactable import EarthInteractable
+from app.models.user import User
+from app.services.earth_interactables import (
+    build_interactable_event,
+    interactables_to_geojson,
+    invalidate_interactable_cache,
+    list_interactables,
+    normalize_interactable_id,
+    publish_interactable_event,
+    serialize_interactable,
+)
+from app.services.earth_layer_cache import (
+    EarthLayerCachePolicy,
+    earth_layer_cache,
+    get_or_build_layer_payload,
+)
+
+router = APIRouter()
+INTERACTABLE_CACHE_POLICY = EarthLayerCachePolicy(
+    fresh_ttl_seconds=60,
+    stale_ttl_seconds=10 * 60,
+    max_features=5000,
+)
+
+
+class InteractableCreate(BaseModel):
+    id: str | None = Field(default=None, max_length=160)
+    layer: str = Field(default="default", min_length=1, max_length=80)
+    kind: str = Field(default="default", min_length=1, max_length=80)
+    label: str = Field(default="", max_length=255)
+    description: str = Field(default="", max_length=4000)
+    latitude: float = Field(ge=-90, le=90)
+    longitude: float = Field(ge=-180, le=180)
+    altitude: float | None = None
+    properties: dict[str, Any] = Field(default_factory=dict)
+
+    @field_validator("layer", "kind")
+    @classmethod
+    def normalize_key(cls, value: str) -> str:
+        normalized = str(value or "").strip()
+        if not normalized:
+            raise ValueError("must not be empty")
+        return normalized
+
+
+class InteractableUpdate(BaseModel):
+    layer: str | None = Field(default=None, min_length=1, max_length=80)
+    kind: str | None = Field(default=None, min_length=1, max_length=80)
+    label: str | None = Field(default=None, max_length=255)
+    description: str | None = Field(default=None, max_length=4000)
+    latitude: float | None = Field(default=None, ge=-90, le=90)
+    longitude: float | None = Field(default=None, ge=-180, le=180)
+    altitude: float | None = None
+    properties: dict[str, Any] | None = None
+
+
+@router.get("")
+async def get_interactables(
+    response: Response,
+    layer: str | None = Query(default=None),
+    include_deleted: bool = Query(default=False),
+    db: AsyncSession = Depends(get_db),
+):
+    items = await list_interactables(db, layer=layer, include_deleted=include_deleted)
+    response.headers["X-Planet-Interactables-Count"] = str(len(items))
+    return {"items": [serialize_interactable(item) for item in items]}
+
+
+@router.get("/geojson")
+async def get_interactables_geojson(
+    response: Response,
+    layer: str | None = Query(default=None),
+    db: AsyncSession = Depends(get_db),
+):
+    async def build_payload() -> dict[str, Any]:
+        items = await list_interactables(db, layer=layer)
+        return interactables_to_geojson(items)
+
+    payload = await get_or_build_layer_payload(
+        key=earth_layer_cache.key("interactables", layer=layer or "all"),
+        policy=INTERACTABLE_CACHE_POLICY,
+        builder=build_payload,
+        response=response,
+    )
+    response.headers["X-Planet-Interactables-Count"] = str(len(payload.get("features") or []))
+    return payload
+
+
+@router.post("", status_code=status.HTTP_201_CREATED)
+async def create_interactable(
+    payload: InteractableCreate,
+    _current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    record_id = normalize_interactable_id(payload.id)
+    existing = await db.get(EarthInteractable, record_id)
+    if existing and not existing.is_deleted:
+        raise HTTPException(status_code=409, detail="Interactable already exists")
+
+    if existing is None:
+        record = EarthInteractable(id=record_id)
+        db.add(record)
+    else:
+        record = existing
+        record.is_deleted = False
+        record.deleted_at = None
+        record.revision += 1
+
+    record.layer = payload.layer
+    record.kind = payload.kind
+    record.label = payload.label
+    record.description = payload.description
+    record.latitude = payload.latitude
+    record.longitude = payload.longitude
+    record.altitude = payload.altitude
+    record.properties = payload.properties
+
+    await db.commit()
+    await db.refresh(record)
+    invalidate_interactable_cache(record.layer)
+    await publish_interactable_event("created", record)
+    return {"item": serialize_interactable(record)}
+
+
+@router.get("/{interactable_id}")
+async def get_interactable(interactable_id: str, db: AsyncSession = Depends(get_db)):
+    record = await db.get(EarthInteractable, interactable_id)
+    if record is None or record.is_deleted:
+        raise HTTPException(status_code=404, detail="Interactable not found")
+    return {"item": serialize_interactable(record)}
+
+
+@router.patch("/{interactable_id}")
+async def update_interactable(
+    interactable_id: str,
+    payload: InteractableUpdate,
+    _current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    record = await db.get(EarthInteractable, interactable_id)
+    if record is None or record.is_deleted:
+        raise HTTPException(status_code=404, detail="Interactable not found")
+
+    previous_layer = record.layer
+    patch = payload.model_dump(exclude_unset=True)
+    for key, value in patch.items():
+        setattr(record, key, value)
+    record.revision += 1
+
+    await db.commit()
+    await db.refresh(record)
+    invalidate_interactable_cache(previous_layer)
+    if record.layer != previous_layer:
+        invalidate_interactable_cache(record.layer)
+    await publish_interactable_event("updated", record)
+    return {"item": serialize_interactable(record)}
+
+
+@router.delete("/{interactable_id}")
+async def delete_interactable(
+    interactable_id: str,
+    _current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    record = await db.get(EarthInteractable, interactable_id)
+    if record is None or record.is_deleted:
+        raise HTTPException(status_code=404, detail="Interactable not found")
+
+    record.is_deleted = True
+    record.deleted_at = datetime.now(UTC)
+    record.revision += 1
+    await db.commit()
+    await db.refresh(record)
+    invalidate_interactable_cache(record.layer)
+    await publish_interactable_event("deleted", record)
+    event = build_interactable_event(action="deleted", record=record, include_item=True)
+    return {"deleted": True, "event": event}

backend/app/api/v1/layers.py

@@ -0,0 +1,231 @@
+from typing import Any, Optional
+
+from fastapi import APIRouter, Depends, HTTPException, Query, Response
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.api.v1.visualization import (
+    _parse_bbox,
+    get_bgp_anomalies_geojson,
+    get_bgp_collectors_geojson,
+    get_bgp_incidents_geojson,
+    get_cables_geojson,
+    get_landing_points_geojson,
+    get_satellites_geojson,
+)
+from app.api.v1.vessels import build_vessel_snapshot_response
+from app.db.session import get_db
+
+router = APIRouter()
+
+DEFAULT_LAYER_LIMIT = 1000
+MAX_LAYER_LIMIT = 5000
+LOW_ZOOM_FEATURE_LIMIT = 500
+
+
+def _clamp_limit(limit: int, zoom: int) -> tuple[int, bool]:
+    clamped = min(max(limit, 1), MAX_LAYER_LIMIT)
+    if zoom <= 3:
+        return min(clamped, LOW_ZOOM_FEATURE_LIMIT), clamped != limit or clamped > LOW_ZOOM_FEATURE_LIMIT
+    return clamped, clamped != limit
+
+
+def _coordinate_in_bbox(coord: Any, bbox: tuple[float, float, float, float]) -> bool:
+    if not isinstance(coord, (list, tuple)) or len(coord) < 2:
+        return False
+    try:
+        lon = float(coord[0])
+        lat = float(coord[1])
+    except (TypeError, ValueError):
+        return False
+    lon_min, lat_min, lon_max, lat_max = bbox
+    return lon_min <= lon <= lon_max and lat_min <= lat <= lat_max
+
+
+def _geometry_intersects_bbox(geometry: dict, bbox: tuple[float, float, float, float]) -> bool:
+    coordinates = geometry.get("coordinates")
+    geometry_type = geometry.get("type")
+    if geometry_type == "Point":
+        return _coordinate_in_bbox(coordinates, bbox)
+    if geometry_type in {"LineString", "MultiPoint"}:
+        return any(_coordinate_in_bbox(coord, bbox) for coord in coordinates or [])
+    if geometry_type in {"Polygon", "MultiLineString"}:
+        return any(
+            _coordinate_in_bbox(coord, bbox)
+            for line in coordinates or []
+            for coord in line
+        )
+    if geometry_type == "MultiPolygon":
+        return any(
+            _coordinate_in_bbox(coord, bbox)
+            for polygon in coordinates or []
+            for line in polygon
+            for coord in line
+        )
+    return False
+
+
+def _guard_geojson_layer(
+    geojson: dict,
+    *,
+    bbox: tuple[float, float, float, float],
+    zoom: int,
+    limit: int,
+) -> dict:
+    bounded_limit, limit_clamped = _clamp_limit(limit, zoom)
+    features = [
+        feature
+        for feature in geojson.get("features", [])
+        if _geometry_intersects_bbox(feature.get("geometry") or {}, bbox)
+    ]
+    visible_count = len(features)
+    returned_features = features[:bounded_limit]
+    return {
+        **geojson,
+        "features": returned_features,
+        "visible_count": visible_count,
+        "returned_count": len(returned_features),
+        "diagnostics": {
+            "bbox_limited": True,
+            "limit": bounded_limit,
+            "limit_clamped": limit_clamped,
+            "truncated": visible_count > len(returned_features),
+            "degraded": zoom <= 3 or visible_count > len(returned_features),
+            "stats_scope": "viewport",
+        },
+    }
+
+
+def _parse_layer_bbox(bbox: str) -> tuple[float, float, float, float]:
+    parsed = _parse_bbox(bbox)
+    if parsed is None:
+        raise HTTPException(status_code=400, detail="bbox is required")
+    return parsed
+
+
+@router.get("/vessels/snapshot")
+async def get_vessel_layer_snapshot(
+    bbox: str = Query(..., description="lon_min,lat_min,lon_max,lat_max"),
+    zoom: int = Query(..., ge=1, le=20),
+    limit: int = Query(DEFAULT_LAYER_LIMIT, ge=1),
+    vessel_type: Optional[str] = Query(None, alias="type"),
+    since_minutes: int = Query(60, ge=1, le=1440),
+    db: AsyncSession = Depends(get_db),
+    response: Response = None,
+):
+    parsed_bbox = _parse_layer_bbox(bbox)
+    return await build_vessel_snapshot_response(
+        db,
+        bbox=parsed_bbox,
+        zoom=zoom,
+        limit=limit,
+        type_filter=vessel_type,
+        since_minutes=since_minutes,
+        response=response,
+    )
+
+
+@router.get("/cables")
+async def get_cable_layer(
+    bbox: str = Query(..., description="lon_min,lat_min,lon_max,lat_max"),
+    zoom: int = Query(..., ge=1, le=20),
+    limit: int = Query(DEFAULT_LAYER_LIMIT, ge=1),
+    db: AsyncSession = Depends(get_db),
+):
+    return _guard_geojson_layer(
+        await get_cables_geojson(db),
+        bbox=_parse_layer_bbox(bbox),
+        zoom=zoom,
+        limit=limit,
+    )
+
+
+@router.get("/landing-points")
+async def get_landing_point_layer(
+    bbox: str = Query(..., description="lon_min,lat_min,lon_max,lat_max"),
+    zoom: int = Query(..., ge=1, le=20),
+    limit: int = Query(DEFAULT_LAYER_LIMIT, ge=1),
+    db: AsyncSession = Depends(get_db),
+):
+    return _guard_geojson_layer(
+        await get_landing_points_geojson(db),
+        bbox=_parse_layer_bbox(bbox),
+        zoom=zoom,
+        limit=limit,
+    )
+
+
+@router.get("/satellites")
+async def get_satellite_layer(
+    bbox: str = Query(..., description="lon_min,lat_min,lon_max,lat_max"),
+    zoom: int = Query(..., ge=1, le=20),
+    limit: int = Query(DEFAULT_LAYER_LIMIT, ge=1),
+    db: AsyncSession = Depends(get_db),
+):
+    bounded_limit, _ = _clamp_limit(limit, zoom)
+    return _guard_geojson_layer(
+        await get_satellites_geojson(limit=bounded_limit, db=db),
+        bbox=_parse_layer_bbox(bbox),
+        zoom=zoom,
+        limit=limit,
+    )
+
+
+@router.get("/bgp/anomalies")
+async def get_bgp_anomaly_layer(
+    bbox: str = Query(..., description="lon_min,lat_min,lon_max,lat_max"),
+    zoom: int = Query(..., ge=1, le=20),
+    limit: int = Query(DEFAULT_LAYER_LIMIT, ge=1),
+    severity: Optional[str] = Query(None),
+    status: Optional[str] = Query("active"),
+    db: AsyncSession = Depends(get_db),
+):
+    bounded_limit, _ = _clamp_limit(limit, zoom)
+    return _guard_geojson_layer(
+        await get_bgp_anomalies_geojson(
+            severity=severity,
+            status=status,
+            limit=bounded_limit,
+            db=db,
+        ),
+        bbox=_parse_layer_bbox(bbox),
+        zoom=zoom,
+        limit=limit,
+    )
+
+
+@router.get("/bgp/incidents")
+async def get_bgp_incident_layer(
+    bbox: str = Query(..., description="lon_min,lat_min,lon_max,lat_max"),
+    zoom: int = Query(..., ge=1, le=20),
+    limit: int = Query(DEFAULT_LAYER_LIMIT, ge=1),
+    severity: Optional[str] = Query(None),
+    status: Optional[str] = Query("active"),
+    db: AsyncSession = Depends(get_db),
+):
+    bounded_limit, _ = _clamp_limit(limit, zoom)
+    return _guard_geojson_layer(
+        await get_bgp_incidents_geojson(
+            severity=severity,
+            status=status,
+            limit=min(bounded_limit, 500),
+            db=db,
+        ),
+        bbox=_parse_layer_bbox(bbox),
+        zoom=zoom,
+        limit=limit,
+    )
+
+
+@router.get("/bgp/collectors")
+async def get_bgp_collector_layer(
+    bbox: str = Query(..., description="lon_min,lat_min,lon_max,lat_max"),
+    zoom: int = Query(..., ge=1, le=20),
+    limit: int = Query(DEFAULT_LAYER_LIMIT, ge=1),
+    db: AsyncSession = Depends(get_db),
+):
+    return _guard_geojson_layer(
+        await get_bgp_collectors_geojson(db),
+        bbox=_parse_layer_bbox(bbox),
+        zoom=zoom,
+        limit=limit,
+    )

backend/app/api/v1/news.py

@@ -1,5 +1,7 @@
-from fastapi import APIRouter, Query
+from fastapi import APIRouter, Depends, Query
+from sqlalchemy.ext.asyncio import AsyncSession
 
+from app.db.session import get_db
 from app.services.earth_news import get_earth_news_payload
 
 router = APIRouter()
@@ -9,5 +11,6 @@ router = APIRouter()
 async def get_earth_feed(
     lat: float | None = Query(None, description="Current Earth view center latitude"),
     lon: float | None = Query(None, description="Current Earth view center longitude"),
+    db: AsyncSession = Depends(get_db),
 ):
-    return await get_earth_news_payload(lat=lat, lon=lon)
+    return await get_earth_news_payload(lat=lat, lon=lon, db=db)

backend/app/api/v1/realtime_sources.py

@@ -0,0 +1,280 @@
+"""Realtime datasource operations and runtime statistics."""
+
+from datetime import UTC, datetime, timedelta
+import os
+from typing import Any
+
+from fastapi import APIRouter, Depends, HTTPException
+from sqlalchemy import distinct, func, select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.core.data_sources import get_data_sources_config
+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.datasource_config import DataSourceConfig
+from app.models.user import User
+from app.models.vessel import AISRawObservation, AISSourceHealth
+from app.services.custom_datasource_runtime import (
+    get_custom_stream_status,
+    start_custom_stream,
+    stop_custom_stream,
+)
+from app.services.scheduler import (
+    cancel_running_collector_now,
+    is_collector_running,
+    run_collector_now,
+)
+from app.services.vessel_ais_aggregation import VESSEL_AIS_SCHEMA, update_ais_source_health
+
+router = APIRouter()
+
+BUILTIN_REALTIME_SOURCES = {"aisstream_vessels"}
+REALTIME_SOURCE_TYPES = {"websocket", "ws"}
+
+
+def _is_realtime_config(config: DataSourceConfig) -> bool:
+    return str(config.source_type or "").lower() in REALTIME_SOURCE_TYPES
+
+
+def _safe_config_dict(value: Any) -> dict[str, Any]:
+    return value if isinstance(value, dict) else {}
+
+
+def _credential_configured(config: DataSourceConfig | None) -> bool:
+    if config is not None:
+        auth_config = _safe_config_dict(config.auth_config)
+        config_payload = _safe_config_dict(config.config)
+        if auth_config.get("api_key") or config_payload.get("api_key"):
+            return True
+    return bool(os.getenv("AISSTREAM_API_KEY"))
+
+
+async def _load_realtime_stats(db: AsyncSession, source: str) -> dict[str, Any]:
+    now = datetime.now(UTC)
+    observed_24h = now - timedelta(hours=24)
+    observed_1h = now - timedelta(hours=1)
+    payload_mmsi = AISRawObservation.entity_key
+
+    result = await db.execute(
+        select(
+            func.count(AISRawObservation.id).label("total_observations"),
+            func.count(AISRawObservation.id)
+            .filter(AISRawObservation.observed_at >= observed_24h)
+            .label("observations_24h"),
+            func.count(AISRawObservation.id)
+            .filter(AISRawObservation.observed_at >= observed_1h)
+            .label("observations_1h"),
+            func.count(distinct(payload_mmsi)).label("unique_mmsi_total"),
+            func.count(distinct(payload_mmsi))
+            .filter(AISRawObservation.observed_at >= observed_24h)
+            .label("unique_mmsi_24h"),
+            func.max(AISRawObservation.observed_at).label("latest_observed_at"),
+            func.max(AISRawObservation.collected_at).label("latest_collected_at"),
+        )
+        .where(AISRawObservation.target_schema == VESSEL_AIS_SCHEMA)
+        .where(AISRawObservation.source == source)
+    )
+    row = result.mappings().one()
+    return {
+        "total_observations": int(row["total_observations"] or 0),
+        "observations_24h": int(row["observations_24h"] or 0),
+        "observations_1h": int(row["observations_1h"] or 0),
+        "unique_mmsi_total": int(row["unique_mmsi_total"] or 0),
+        "unique_mmsi_24h": int(row["unique_mmsi_24h"] or 0),
+        "latest_observed_at": to_iso8601_utc(row["latest_observed_at"]),
+        "latest_collected_at": to_iso8601_utc(row["latest_collected_at"]),
+    }
+
+
+def _runtime_status_for_builtin(source: str) -> dict[str, Any]:
+    running = is_collector_running(source)
+    return {
+        "running": running,
+        "done": False,
+        "runtime": "collector",
+    }
+
+
+def _runtime_status_for_custom(config_id: int) -> dict[str, Any]:
+    status = get_custom_stream_status(config_id)
+    return {
+        "running": bool(status.get("running")),
+        "done": bool(status.get("done")),
+        "runtime": "custom_stream",
+    }
+
+
+async def _serialize_builtin_aisstream(
+    db: AsyncSession,
+    datasource: DataSource,
+    config: DataSourceConfig | None,
+) -> dict[str, Any]:
+    health = await db.get(AISSourceHealth, datasource.source)
+    config_payload = _safe_config_dict(config.config if config else {})
+    endpoint = (
+        (config.endpoint if config else None)
+        or get_data_sources_config().get_yaml_url(datasource.source)
+    )
+    return {
+        "source": datasource.source,
+        "name": datasource.name,
+        "display_name": "AISStream 实时船舶",
+        "kind": "builtin",
+        "source_type": "websocket",
+        "endpoint": endpoint,
+        "is_active": bool(datasource.is_active),
+        "credential_configured": _credential_configured(config),
+        "message_types": config_payload.get("message_types") or ["PositionReport", "ShipStaticData"],
+        "bounding_boxes": config_payload.get("bounding_boxes") or [[[-90, -180], [90, 180]]],
+        "config": config_payload,
+        "runtime": _runtime_status_for_builtin(datasource.source),
+        "health": health.to_dict() if health else None,
+        "stats": await _load_realtime_stats(db, datasource.source),
+    }
+
+
+async def _serialize_custom_stream(
+    db: AsyncSession,
+    config: DataSourceConfig,
+) -> dict[str, Any]:
+    health = await db.get(AISSourceHealth, config.name)
+    config_payload = _safe_config_dict(config.config)
+    return {
+        "source": config.name,
+        "name": config.name,
+        "display_name": config.description or config.name,
+        "kind": "custom",
+        "config_id": config.id,
+        "source_type": config.source_type,
+        "endpoint": config.endpoint,
+        "is_active": bool(config.is_active),
+        "credential_configured": config.auth_type == "none" or bool(_safe_config_dict(config.auth_config)),
+        "message_types": config_payload.get("message_types") or [],
+        "bounding_boxes": config_payload.get("bounding_boxes") or [],
+        "config": config_payload,
+        "runtime": _runtime_status_for_custom(config.id),
+        "health": health.to_dict() if health else None,
+        "stats": await _load_realtime_stats(db, config.name),
+    }
+
+
+async def _load_builtin_aisstream(db: AsyncSession) -> tuple[DataSource | None, DataSourceConfig | None]:
+    result = await db.execute(select(DataSource).where(DataSource.source == "aisstream_vessels"))
+    datasource = result.scalar_one_or_none()
+    config_result = await db.execute(
+        select(DataSourceConfig)
+        .where(DataSourceConfig.name == "aisstream_vessels")
+        .where(DataSourceConfig.is_active.is_(True))
+        .order_by(DataSourceConfig.id.desc())
+        .limit(1)
+    )
+    return datasource, config_result.scalar_one_or_none()
+
+
+async def _load_custom_realtime_config(db: AsyncSession, source: str) -> DataSourceConfig | None:
+    result = await db.execute(
+        select(DataSourceConfig)
+        .where(DataSourceConfig.name == source)
+        .order_by(DataSourceConfig.id.desc())
+        .limit(1)
+    )
+    config = result.scalar_one_or_none()
+    return config if config is not None and _is_realtime_config(config) else None
+
+
+@router.get("")
+async def list_realtime_sources(
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    sources: list[dict[str, Any]] = []
+    datasource, builtin_config = await _load_builtin_aisstream(db)
+    if datasource is not None:
+        sources.append(await _serialize_builtin_aisstream(db, datasource, builtin_config))
+
+    custom_result = await db.execute(
+        select(DataSourceConfig)
+        .where(func.lower(DataSourceConfig.source_type).in_(REALTIME_SOURCE_TYPES))
+        .order_by(DataSourceConfig.name)
+    )
+    for config in custom_result.scalars().all():
+        if config.name in BUILTIN_REALTIME_SOURCES:
+            continue
+        sources.append(await _serialize_custom_stream(db, config))
+
+    return {"total": len(sources), "data": sources}
+
+
+async def _ensure_builtin_startable(db: AsyncSession) -> DataSourceConfig | None:
+    datasource, config = await _load_builtin_aisstream(db)
+    if datasource is None:
+        raise HTTPException(status_code=404, detail="Realtime source not found")
+    if not datasource.is_active:
+        raise HTTPException(status_code=400, detail="Realtime source is disabled")
+    if not _credential_configured(config):
+        raise HTTPException(status_code=400, detail="AISStream API key is not configured")
+    return config
+
+
+@router.post("/{source}/start")
+async def start_realtime_source(
+    source: str,
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    if source == "aisstream_vessels":
+        await _ensure_builtin_startable(db)
+        if is_collector_running(source):
+            return {"status": "already_running", "source": source, "runtime": _runtime_status_for_builtin(source)}
+        if not run_collector_now(source):
+            raise HTTPException(status_code=409, detail="Realtime source could not be started")
+        return {"status": "started", "source": source, "runtime": _runtime_status_for_builtin(source)}
+
+    config = await _load_custom_realtime_config(db, source)
+    if config is None:
+        raise HTTPException(status_code=404, detail="Realtime source not found")
+    if not config.is_active:
+        raise HTTPException(status_code=400, detail="Realtime source is disabled")
+    started = start_custom_stream(config.id)
+    return {
+        "status": "started" if started else "already_running",
+        "source": source,
+        "runtime": _runtime_status_for_custom(config.id),
+    }
+
+
+@router.post("/{source}/stop")
+async def stop_realtime_source(
+    source: str,
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    if source == "aisstream_vessels":
+        stopped = await cancel_running_collector_now(source)
+        await update_ais_source_health(db, source=source, connection_state="disconnected", last_error=None)
+        await db.commit()
+        return {"status": "stopped" if stopped else "not_running", "source": source, "runtime": _runtime_status_for_builtin(source)}
+
+    config = await _load_custom_realtime_config(db, source)
+    if config is None:
+        raise HTTPException(status_code=404, detail="Realtime source not found")
+    stopped = await stop_custom_stream(config.id)
+    await update_ais_source_health(db, source=source, connection_state="disconnected", last_error=None)
+    await db.commit()
+    return {
+        "status": "stopped" if stopped else "not_running",
+        "source": source,
+        "runtime": _runtime_status_for_custom(config.id),
+    }
+
+
+@router.post("/{source}/restart")
+async def restart_realtime_source(
+    source: str,
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    await stop_realtime_source(source, current_user=current_user, db=db)
+    return await start_realtime_source(source, current_user=current_user, db=db)

backend/app/api/v1/system_control.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import os
+import json
 import subprocess
 import sys
 
@@ -8,9 +9,13 @@ from datetime import datetime
 
 from fastapi import APIRouter, Depends, HTTPException, Query, Request, status
 from pydantic import BaseModel
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.core.config import ROOT_DIR
 from app.core.security import get_current_user
+from app.db.session import get_db
+from app.models.system_log import AuditLog, SystemLog
 from app.models.user import User
 from app.services.persistent_logs import record_audit_log, record_system_log
 from app.services.system_control import (
@@ -35,10 +40,47 @@ from app.services.system_logs import (
     normalize_log_level,
     read_log_snapshot,
 )
+from app.services.earth_layer_cache import earth_layer_cache
 
 router = APIRouter()
 
 
+def _compact_log_context(context: dict | None) -> str:
+    if not context:
+        return ""
+    allowed = {
+        key: value
+        for key, value in (context or {}).items()
+        if key
+        in {
+            "status",
+            "duration_ms",
+            "provider",
+            "model",
+            "result_provider",
+            "result_model",
+            "collector_name",
+            "datasource_id",
+            "task_id",
+            "snapshot_id",
+            "raw_count",
+            "transformed_count",
+            "saved_count",
+            "created",
+            "updated",
+            "unchanged",
+            "deleted",
+            "result_count",
+            "status_code",
+            "error_type",
+            "error",
+        }
+    }
+    if not allowed:
+        return ""
+    return json.dumps(allowed, ensure_ascii=False, sort_keys=True)
+
+
 class RestartTaskCreate(BaseModel):
     action: str
 
@@ -112,6 +154,17 @@ class EarthClientLogEventResponse(BaseModel):
     level: str
 
 
+class EarthLayerCacheStatusResponse(BaseModel):
+    prefix: str
+    key_count: int
+    memory_bytes: int
+    layers: dict[str, dict[str, int]]
+
+
+class EarthLayerCacheClearResponse(BaseModel):
+    deleted: int
+
+
 def ensure_super_admin(current_user: User) -> None:
     if not require_super_admin(current_user.role):
         raise HTTPException(
@@ -132,6 +185,34 @@ def validate_log_date(raw_value: str | None, field_name: str) -> str | None:
         ) from exc
 
 
+@router.get("/cache/earth-layers", response_model=EarthLayerCacheStatusResponse)
+async def get_earth_layer_cache_status(
+    current_user: User = Depends(get_current_user),
+):
+    ensure_super_admin(current_user)
+    try:
+        return earth_layer_cache.status()
+    except Exception as exc:
+        raise HTTPException(
+            status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
+            detail=f"Unable to read Earth layer cache status: {exc}",
+        ) from exc
+
+
+@router.delete("/cache/earth-layers", response_model=EarthLayerCacheClearResponse)
+async def clear_earth_layer_cache(
+    current_user: User = Depends(get_current_user),
+):
+    ensure_super_admin(current_user)
+    try:
+        return {"deleted": earth_layer_cache.delete_pattern()}
+    except Exception as exc:
+        raise HTTPException(
+            status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
+            detail=f"Unable to clear Earth layer cache: {exc}",
+        ) from exc
+
+
 @router.post("/restart-tasks", response_model=RestartTaskResponse)
 async def create_restart_task(
     payload: RestartTaskCreate,
@@ -270,7 +351,123 @@ async def get_system_log_sources(
     current_user: User = Depends(get_current_user),
 ):
     ensure_super_admin(current_user)
-    return {"items": list_log_sources()}
+    return {
+        "items": [
+            *list_log_sources(),
+            {
+                "source_id": "system-db",
+                "name": "系统事件",
+                "kind": "database",
+                "location": "table://system_logs",
+                "description": "后端持久化系统事件、AI 和采集器操作日志。",
+                "category": "database",
+                "status": "ok",
+            },
+            {
+                "source_id": "audit-db",
+                "name": "审计事件",
+                "kind": "database",
+                "location": "table://audit_logs",
+                "description": "管理员敏感操作和密钥 reveal 审计记录。",
+                "category": "audit",
+                "status": "ok",
+            },
+        ]
+    }
+
+
+async def read_database_log_snapshot(
+    source_id: str,
+    *,
+    limit: int,
+    level: str,
+    levels: str | None,
+    start_date: str | None,
+    end_date: str | None,
+    search: str | None,
+    db: AsyncSession,
+) -> dict | None:
+    selected_levels = set(normalize_log_level(item) for item in (levels or level).split(",") if item.strip())
+    selected_levels.discard("all")
+    search_query = (search or "").strip().lower()
+    lines: list[str] = []
+
+    if source_id == "system-db":
+        query = select(SystemLog).order_by(SystemLog.occurred_at.desc().nullslast(), SystemLog.id.desc()).limit(limit * 5)
+        result = await db.execute(query)
+        records = result.scalars().all()
+        for record in records:
+            record_level = normalize_log_level(record.level)
+            if selected_levels and record_level not in selected_levels:
+                continue
+            occurred_at = record.occurred_at.date().isoformat() if record.occurred_at else ""
+            if start_date and occurred_at and occurred_at < start_date:
+                continue
+            if end_date and occurred_at and occurred_at > end_date:
+                continue
+            line = " ".join(
+                part
+                for part in [
+                    record.occurred_at.isoformat() if record.occurred_at else "",
+                    record_level.upper(),
+                    record.source,
+                    record.category or "",
+                    record.event or "",
+                    f"request_id={record.request_id}" if record.request_id else "",
+                    record.message,
+                    _compact_log_context(record.context),
+                ]
+                if part
+            )
+            if search_query and search_query not in line.lower():
+                continue
+            lines.append(line)
+    elif source_id == "audit-db":
+        query = select(AuditLog).order_by(AuditLog.occurred_at.desc().nullslast(), AuditLog.id.desc()).limit(limit * 5)
+        result = await db.execute(query)
+        records = result.scalars().all()
+        for record in records:
+            occurred_at = record.occurred_at.date().isoformat() if record.occurred_at else ""
+            if start_date and occurred_at and occurred_at < start_date:
+                continue
+            if end_date and occurred_at and occurred_at > end_date:
+                continue
+            line = " ".join(
+                part
+                for part in [
+                    record.occurred_at.isoformat() if record.occurred_at else "",
+                    "INFO",
+                    record.action,
+                    record.target_type or "",
+                    record.target_id or "",
+                    record.result or "",
+                ]
+                if part
+            )
+            if search_query and search_query not in line.lower():
+                continue
+            lines.append(line)
+    else:
+        return None
+
+    lines = list(reversed(lines[:limit]))
+    return {
+        "source_id": source_id,
+        "name": "系统事件" if source_id == "system-db" else "审计事件",
+        "kind": "database",
+        "location": "table://system_logs" if source_id == "system-db" else "table://audit_logs",
+        "description": "数据库持久化日志",
+        "category": "database" if source_id == "system-db" else "audit",
+        "status": "ok" if lines else "empty",
+        "level": level,
+        "selected_levels": sorted(selected_levels),
+        "search_query": search or "",
+        "available_levels": ["all", "error", "warning", "info", "debug"],
+        "daily_markers": [],
+        "line_limit": limit,
+        "line_count": len(lines),
+        "lines": lines,
+    }
 
 
 @router.get("/logs/{source_id}", response_model=SystemLogSnapshotResponse)
@@ -283,6 +480,7 @@ async def get_system_log_snapshot(
     end_date: str | None = Query(None, description="Filter logs until this date (YYYY-MM-DD)"),
     search: str | None = Query(None, description="Case-insensitive substring search"),
     current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
 ):
     ensure_super_admin(current_user)
 
@@ -305,15 +503,26 @@ async def get_system_log_snapshot(
     if normalized_start_date and normalized_end_date and normalized_start_date > normalized_end_date:
         raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="start_date must be earlier than or equal to end_date")
 
-    snapshot = read_log_snapshot(
+    snapshot = await read_database_log_snapshot(
         source_id,
-        limit,
+        limit=limit,
         level=level,
         levels=levels,
         start_date=normalized_start_date,
         end_date=normalized_end_date,
         search=search,
+        db=db,
     )
+    if snapshot is None:
+        snapshot = read_log_snapshot(
+            source_id,
+            limit,
+            level=level,
+            levels=levels,
+            start_date=normalized_start_date,
+            end_date=normalized_end_date,
+            search=search,
+        )
     if snapshot is None:
         raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Log source not found")
     return snapshot

backend/app/api/v1/vessels.py

@@ -0,0 +1,41 @@
+"""Bounded vessel snapshot APIs for viewport-first consumers."""
+
+from typing import Optional
+
+from fastapi import APIRouter, Depends, HTTPException, Query, Response
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.api.v1.visualization import _parse_bbox, build_vessel_snapshot_response
+from app.db.session import get_db
+from app.services.vessel_ais_aggregation import MAX_SNAPSHOT_LIMIT
+
+router = APIRouter()
+
+
+@router.get("/snapshot")
+async def get_vessel_snapshot(
+    bbox: Optional[str] = Query(None, description="Viewport bbox as lon_min,lat_min,lon_max,lat_max"),
+    zoom: int = Query(..., ge=1, le=20, description="Current map zoom level"),
+    type: Optional[str] = Query(
+        None,
+        description="Comma-separated vessel types: cargo,tanker,passenger,fishing,military,other",
+    ),
+    limit: int = Query(1000, ge=1, le=MAX_SNAPSHOT_LIMIT),
+    since_minutes: int = Query(60, ge=1, le=1440),
+    db: AsyncSession = Depends(get_db),
+    response: Response = None,
+):
+    if not bbox:
+        raise HTTPException(status_code=400, detail="bbox is required")
+    parsed_bbox = _parse_bbox(bbox)
+    if parsed_bbox is None:
+        raise HTTPException(status_code=400, detail="bbox is required")
+    return await build_vessel_snapshot_response(
+        db,
+        bbox=parsed_bbox,
+        zoom=zoom,
+        type_filter=type,
+        limit=limit,
+        since_minutes=since_minutes,
+        response=response,
+    )

backend/app/api/v1/visualization.py

@@ -31,12 +31,19 @@ from app.services.cable_graph import build_graph_from_data, CableGraph, haversin
 from app.services.compute_center_locations import (
     RENDERABLE_PRECISIONS,
     ResolutionDiagnostic,
+    build_compute_center_location_query,
     collect_location_candidates,
     refresh_compute_center_location_cache,
     resolve_compute_center_location_full,
     upsert_compute_center_location,
 )
+from app.services.ai_client import get_ai_provider_client
+from app.api.v1.settings import get_runtime_web_search_config, get_web_search_client
 from app.services.collectors.bgp_common import RIPE_RIS_COLLECTOR_COORDS
+from app.services.location.llm_fallback import (
+    collect_llm_location_fallback_candidate,
+    collect_location_search_evidence,
+)
 from app.services.persistent_logs import record_system_log
 from app.services.vessel_ais_aggregation import (
     build_field_conflict_candidates,
@@ -44,8 +51,17 @@ from app.services.vessel_ais_aggregation import (
     get_aggregated_vessel,
     get_aggregated_vessel_track,
     get_aggregated_vessels,
+    get_aggregated_vessels_snapshot,
     get_vessel_conflict_records,
     get_vessel_raw_observations,
+    MAX_SNAPSHOT_LIMIT,
+)
+from app.services.earth_layer_cache import (
+    EarthLayerCachePolicy,
+    earth_layer_cache,
+    format_bbox_key,
+    get_or_build_layer_payload,
+    quantize_bbox,
 )
 from app.core.logging import get_logger
 
@@ -59,6 +75,69 @@ TERRAIN_TILE_BATCH_MAX_ITEMS = 128
 TERRAIN_TILE_BATCH_CONCURRENCY = 16
 _terrain_tile_cache: OrderedDict[tuple[int, int, int], tuple[bytes, str, dict[str, str]]] = OrderedDict()
 VESSEL_NAME_FALLBACK_PATTERN = re.compile(r"^mmsi\s*\d+$", re.IGNORECASE)
+VESSEL_SNAPSHOT_LEGACY_FALLBACK_ENABLED = True
+SECONDS_PER_MINUTE = 60
+BYTES_PER_MIB = 1024 * 1024
+CABLE_CACHE_FRESH_SECONDS = 6 * 60 * SECONDS_PER_MINUTE
+CABLE_CACHE_STALE_SECONDS = 24 * 60 * SECONDS_PER_MINUTE
+SATELLITE_CACHE_FRESH_SECONDS = 15 * SECONDS_PER_MINUTE
+SATELLITE_CACHE_STALE_SECONDS = 2 * 60 * SECONDS_PER_MINUTE
+COMPUTE_CENTER_CACHE_FRESH_SECONDS = 10 * SECONDS_PER_MINUTE
+COMPUTE_CENTER_CACHE_STALE_SECONDS = 60 * SECONDS_PER_MINUTE
+BGP_CACHE_FRESH_SECONDS = 60
+BGP_EVENT_CACHE_FRESH_SECONDS = 30
+BGP_CACHE_STALE_SECONDS = 10 * SECONDS_PER_MINUTE
+VESSEL_SNAPSHOT_CACHE_FRESH_SECONDS = 5
+VESSEL_SNAPSHOT_CACHE_STALE_SECONDS = 30
+
+CABLE_CACHE_POLICY = EarthLayerCachePolicy(
+    CABLE_CACHE_FRESH_SECONDS,
+    CABLE_CACHE_STALE_SECONDS,
+    max_features=6000,
+    max_bytes=10 * BYTES_PER_MIB,
+)
+LANDING_POINT_CACHE_POLICY = EarthLayerCachePolicy(
+    CABLE_CACHE_FRESH_SECONDS,
+    CABLE_CACHE_STALE_SECONDS,
+    max_features=6000,
+    max_bytes=8 * BYTES_PER_MIB,
+)
+SATELLITE_CACHE_POLICY = EarthLayerCachePolicy(
+    SATELLITE_CACHE_FRESH_SECONDS,
+    SATELLITE_CACHE_STALE_SECONDS,
+    max_features=25000,
+    max_bytes=32 * BYTES_PER_MIB,
+)
+COMPUTE_CENTER_CACHE_POLICY = EarthLayerCachePolicy(
+    COMPUTE_CENTER_CACHE_FRESH_SECONDS,
+    COMPUTE_CENTER_CACHE_STALE_SECONDS,
+    max_features=1000,
+    max_bytes=4 * BYTES_PER_MIB,
+)
+BGP_CACHE_POLICY = EarthLayerCachePolicy(
+    BGP_CACHE_FRESH_SECONDS,
+    BGP_CACHE_STALE_SECONDS,
+    max_features=1000,
+    max_bytes=3 * BYTES_PER_MIB,
+)
+BGP_EVENT_CACHE_POLICY = EarthLayerCachePolicy(
+    BGP_EVENT_CACHE_FRESH_SECONDS,
+    BGP_CACHE_STALE_SECONDS,
+    max_features=1000,
+    max_bytes=3 * BYTES_PER_MIB,
+)
+SUMMARY_CACHE_POLICY = EarthLayerCachePolicy(
+    BGP_EVENT_CACHE_FRESH_SECONDS,
+    BGP_CACHE_STALE_SECONDS,
+    max_features=0,
+    max_bytes=512 * 1024,
+)
+VESSEL_SNAPSHOT_CACHE_POLICY = EarthLayerCachePolicy(
+    VESSEL_SNAPSHOT_CACHE_FRESH_SECONDS,
+    VESSEL_SNAPSHOT_CACHE_STALE_SECONDS,
+    max_features=1500,
+    max_bytes=3 * BYTES_PER_MIB,
+)
 
 
 class TerrariumTileRequest(BaseModel):
@@ -932,6 +1011,39 @@ def _merge_vessel_features(
     }
 
 
+async def _load_legacy_vessel_snapshot_features(
+    db: AsyncSession,
+    *,
+    bbox: tuple[float, float, float, float] | None,
+    limit: int,
+) -> list[dict[str, Any]]:
+    latest_positions = select(
+        VesselPosition.mmsi.label("mmsi"),
+        func.max(VesselPosition.received_at).label("received_at"),
+    )
+    if bbox is not None:
+        lon_min, lat_min, lon_max, lat_max = bbox
+        latest_positions = latest_positions.where(VesselPosition.lon >= lon_min)
+        latest_positions = latest_positions.where(VesselPosition.lon <= lon_max)
+        latest_positions = latest_positions.where(VesselPosition.lat >= lat_min)
+        latest_positions = latest_positions.where(VesselPosition.lat <= lat_max)
+
+    latest_positions = latest_positions.group_by(VesselPosition.mmsi).subquery()
+    result = await db.execute(
+        select(VesselPosition, VesselStatic)
+        .join(
+            latest_positions,
+            (VesselPosition.mmsi == latest_positions.c.mmsi)
+            & (VesselPosition.received_at == latest_positions.c.received_at),
+        )
+        .outerjoin(VesselStatic, VesselStatic.mmsi == VesselPosition.mmsi)
+        .order_by(VesselPosition.received_at.desc())
+        .limit(limit)
+    )
+    legacy_geojson = convert_vessels_to_geojson(list(result.all()))
+    return legacy_geojson.get("features", [])[:limit]
+
+
 def _build_vessel_stats(features: List[dict[str, Any]]) -> dict[str, Any]:
     by_type: dict[str, int] = {}
     underway = 0
@@ -953,6 +1065,85 @@ def _build_vessel_stats(features: List[dict[str, Any]]) -> dict[str, Any]:
     }
 
 
+def _safe_vessel_limit(value: int | None, *, default: int = 1000) -> int:
+    if value is None or value <= 0:
+        return default
+    return min(value, MAX_SNAPSHOT_LIMIT)
+
+
+async def build_vessel_snapshot_response(
+    db: AsyncSession,
+    *,
+    bbox: tuple[float, float, float, float] | None,
+    zoom: int | None,
+    type_filter: str | None,
+    limit: int | None,
+    since_minutes: int = 60,
+    response: Response | None = None,
+    use_cache: bool = True,
+) -> dict[str, Any]:
+    if use_cache and bbox is not None:
+        safe_limit_for_key = _safe_vessel_limit(limit)
+        safe_since_for_key = min(max(int(since_minutes or 60), 1), 1440)
+        cache_key = earth_layer_cache.key(
+            "vessels-snapshot",
+            bbox=format_bbox_key(quantize_bbox(bbox)),
+            zoom=zoom or "none",
+            type=type_filter or "all",
+            limit=safe_limit_for_key,
+            since=safe_since_for_key,
+        )
+
+        async def build_uncached() -> dict[str, Any]:
+            return await build_vessel_snapshot_response(
+                db,
+                bbox=bbox,
+                zoom=zoom,
+                type_filter=type_filter,
+                limit=limit,
+                since_minutes=since_minutes,
+                response=None,
+                use_cache=False,
+            )
+
+        return await get_or_build_layer_payload(
+            key=cache_key,
+            policy=VESSEL_SNAPSHOT_CACHE_POLICY,
+            builder=build_uncached,
+            response=response,
+        )
+
+    requested_types = _requested_vessel_types(type_filter)
+    safe_limit = _safe_vessel_limit(limit)
+    safe_since_minutes = min(max(int(since_minutes or 60), 1), 1440)
+    observed_since = datetime.now(UTC) - timedelta(minutes=safe_since_minutes)
+    features, diagnostics = await _load_raw_vessel_snapshot_features(
+        db,
+        bbox=bbox,
+        limit=safe_limit,
+        observed_since=observed_since,
+    )
+    features = _filter_vessel_features(
+        features,
+        bbox=bbox,
+        requested_types=requested_types,
+    )[:safe_limit]
+    return {
+        "type": "FeatureCollection",
+        "features": features,
+        "count": len(features),
+        "stats": _build_vessel_stats(features),
+        "diagnostics": {
+            **diagnostics,
+            "filtered_count": len(features),
+            "bbox_applied": bbox is not None,
+            "zoom": zoom,
+            "limit": safe_limit,
+            "since_minutes": safe_since_minutes,
+        },
+    }
+
+
 def convert_bgp_anomalies_to_geojson(
     records: List[BGPAnomaly],
     geography_hints: Optional[Dict[str, Dict[str, Any]]] = None,
@@ -1355,20 +1546,24 @@ def convert_bgp_incidents_to_geojson(
 
 
 @router.get("/geo/cables")
-async def get_cables_geojson(db: AsyncSession = Depends(get_db)):
+async def get_cables_geojson(db: AsyncSession = Depends(get_db), response: Response = None):
     """获取海底电缆 GeoJSON 数据 (LineString)"""
+    async def build_payload() -> dict[str, Any]:
+        return await _build_cables_geojson(db)
+
+    return await get_or_build_layer_payload(
+        key=earth_layer_cache.key("cables"),
+        policy=CABLE_CACHE_POLICY,
+        builder=build_payload,
+        response=response,
+    )
+
+
+async def _build_cables_geojson(db: AsyncSession) -> dict[str, Any]:
     try:
         records = await _load_current_collected_data(db, "arcgis_cables")
 
-        if not records:
-            raise HTTPException(
-                status_code=404,
-                detail="No cable data found. Please run the arcgis_cables collector first.",
-            )
-
         return convert_cable_to_geojson(records)
-    except HTTPException:
-        raise
     except Exception as e:
         logger.exception_event(
             "Failed to build cables GeoJSON response",
@@ -1389,7 +1584,19 @@ 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)):
+async def get_landing_points_geojson(db: AsyncSession = Depends(get_db), response: Response = None):
+    async def build_payload() -> dict[str, Any]:
+        return await _build_landing_points_geojson(db)
+
+    return await get_or_build_layer_payload(
+        key=earth_layer_cache.key("landing-points"),
+        policy=LANDING_POINT_CACHE_POLICY,
+        builder=build_payload,
+        response=response,
+    )
+
+
+async def _build_landing_points_geojson(db: AsyncSession) -> dict[str, Any]:
     try:
         records_by_source = await _load_current_collected_data_by_sources(
             db,
@@ -1410,16 +1617,8 @@ async def get_landing_points_geojson(db: AsyncSession = Depends(get_db)):
             relation_records,
             cable_records,
         )
-        
-        if not records:
-            raise HTTPException(
-                status_code=404,
-                detail="No landing point data found. Please run the arcgis_landing_points collector first.",
-            )
-        
+
         return convert_landing_point_to_geojson(records, city_to_cable_ids_map, cable_id_to_name_map)
-    except HTTPException:
-        raise
     except Exception as e:
         logger.exception_event(
             "Failed to build landing points GeoJSON response",
@@ -1642,8 +1841,25 @@ async def get_satellites_geojson(
         description="Maximum number of satellites to return. Omit for no limit.",
     ),
     db: AsyncSession = Depends(get_db),
+    response: Response = None,
 ):
     """获取卫星 TLE GeoJSON 数据"""
+    async def build_payload() -> dict[str, Any]:
+        return await _build_satellites_geojson(limit=limit, db=db)
+
+    return await get_or_build_layer_payload(
+        key=earth_layer_cache.key("satellites", limit=limit or "all"),
+        policy=SATELLITE_CACHE_POLICY,
+        builder=build_payload,
+        response=response,
+    )
+
+
+async def _build_satellites_geojson(
+    *,
+    limit: int | None,
+    db: AsyncSession,
+) -> dict[str, Any]:
     records = await _load_current_or_latest_task_data(
         db,
         "celestrak_tle",
@@ -1711,8 +1927,25 @@ async def get_gpu_clusters_geojson(
 async def get_compute_centers_geojson(
     limit: int = Query(200, ge=1, le=1000),
     db: AsyncSession = Depends(get_db),
+    response: Response = None,
 ):
     """获取统一算力中心 GeoJSON 数据"""
+    async def build_payload() -> dict[str, Any]:
+        return await _build_compute_centers_geojson(limit=limit, db=db)
+
+    return await get_or_build_layer_payload(
+        key=earth_layer_cache.key("compute-centers", limit=limit),
+        policy=COMPUTE_CENTER_CACHE_POLICY,
+        builder=build_payload,
+        response=response,
+    )
+
+
+async def _build_compute_centers_geojson(
+    *,
+    limit: int,
+    db: AsyncSession,
+) -> dict[str, Any]:
     records_by_source = await _load_current_collected_data_by_sources(
         db,
         ["top500", "epoch_ai_gpu"],
@@ -1822,6 +2055,44 @@ class SaveComputeCenterLocationRequest(BaseModel):
     model_config = {"populate_by_name": True}
 
 
+async def _compute_center_location_web_search_capability(db: AsyncSession) -> Dict[str, Any]:
+    try:
+        config = await get_runtime_web_search_config(db)
+    except Exception as exc:
+        return {
+            "enabled": False,
+            "provider": None,
+            "reason": f"WebSearch 配置读取失败：{exc}",
+        }
+    provider_config = config.active_provider_config
+    has_api_key = bool((provider_config.api_key or "").strip())
+    if not config.enabled:
+        return {
+            "enabled": False,
+            "provider": config.default_provider,
+            "reason": "WebSearch 未开启，无法进行事实核查定位。",
+        }
+    if not has_api_key:
+        return {
+            "enabled": False,
+            "provider": config.default_provider,
+            "reason": f"WebSearch Provider {config.default_provider} 未配置 API Key。",
+        }
+    return {
+        "enabled": True,
+        "provider": config.default_provider,
+        "reason": "",
+    }
+
+
+@router.get("/compute-centers/location-capability")
+async def get_compute_center_location_capability(
+    db: AsyncSession = Depends(get_db),
+):
+    """Return whether fact-checked compute-center location collection can run."""
+    return await _compute_center_location_web_search_capability(db)
+
+
 @router.post("/compute-centers/{source_id}/collect-location")
 async def collect_compute_center_location(
     source_id: str,
@@ -1840,6 +2111,9 @@ async def collect_compute_center_location(
     """
     if not source_id or not source_id.strip():
         raise HTTPException(status_code=400, detail="source_id is required")
+    capability = await _compute_center_location_web_search_capability(db)
+    if not capability.get("enabled"):
+        raise HTTPException(status_code=409, detail=capability)
 
     record = await _load_compute_center_record(db, source_id)
     name = payload.name or (record.name if record else None)
@@ -1864,8 +2138,70 @@ async def collect_compute_center_location(
         country=country,
         record_id=record_id,
     )
+    llm_failure_reason = None
+    if not candidates:
+        query = build_compute_center_location_query(
+            name=name,
+            source=source,
+            source_id=source_id,
+            operator=operator,
+            site=site,
+            organization=organization,
+            city=city,
+            country=country,
+        )
+        llm_result = None
+        try:
+            web_search_client = await get_web_search_client(db)
+            search_result = await collect_location_search_evidence(
+                web_search_client=web_search_client,
+                query=query,
+                entity_type="compute_center",
+            )
+            attempted_queries = [*attempted_queries, *search_result.attempted_queries]
+            if not search_result.evidence:
+                llm_failure_reason = search_result.failure_reason
+                raise RuntimeError(search_result.failure_reason or "no WebSearch evidence")
+            provider_client = await get_ai_provider_client(db)
+            llm_result = await collect_llm_location_fallback_candidate(
+                provider_client=provider_client,
+                query=query,
+                entity_type="compute_center",
+                db=db,
+                attempted_queries=attempted_queries,
+                search_evidence=search_result.evidence,
+            )
+        except Exception as exc:
+            if llm_failure_reason is None:
+                llm_failure_reason = f"LLM location factcheck unavailable: {exc}"
+                attempted_queries = [
+                    *attempted_queries,
+                    f"llm_factcheck:compute_center:{name or source_id or 'unknown'}",
+                ]
+        if llm_result is not None:
+            attempted_queries = [*attempted_queries, *llm_result.attempted_queries]
+            candidates = llm_result.candidates
+            llm_failure_reason = llm_result.failure_reason
 
     if not candidates:
+        logger.warning_event(
+            "Compute center location collection returned no candidates",
+            event="visualization.compute_center.location_collect.completed",
+            context={
+                "source_id": source_id,
+                "record_id": record_id,
+                "name": name,
+                "success": False,
+                "llm_failure_reason": llm_failure_reason,
+                "attempted_queries": list(attempted_queries),
+                "context": {
+                    "operator": operator,
+                    "site": site,
+                    "city": city,
+                    "country": country,
+                },
+            },
+        )
         return {
             "source_id": source_id,
             "record_id": record_id,
@@ -1877,6 +2213,7 @@ async def collect_compute_center_location(
             ),
             "candidates": [],
             "attempted_queries": list(attempted_queries),
+            "llm_failure_reason": llm_failure_reason,
             "context": {
                 "name": name,
                 "operator": operator,
@@ -1886,13 +2223,34 @@ async def collect_compute_center_location(
             },
         }
 
+    best_candidate = candidates[0].to_dict()
+    logger.info_event(
+        "Compute center location collection returned candidates",
+        event="visualization.compute_center.location_collect.completed",
+        context={
+            "source_id": source_id,
+            "record_id": record_id,
+            "name": name,
+            "success": True,
+            "candidate_count": len(candidates),
+            "best_candidate": best_candidate,
+            "llm_failure_reason": llm_failure_reason,
+            "attempted_queries": list(attempted_queries),
+            "context": {
+                "operator": operator,
+                "site": site,
+                "city": city,
+                "country": country,
+            },
+        },
+    )
     return {
         "source_id": source_id,
         "record_id": record_id,
         "name": name,
         "success": True,
         "candidates": [candidate.to_dict() for candidate in candidates],
-        "best_candidate": candidates[0].to_dict(),
+        "best_candidate": best_candidate,
         "attempted_queries": list(attempted_queries),
         "context": {
             "name": name,
@@ -1974,83 +2332,68 @@ async def _load_compute_center_record(db: AsyncSession, source_id: str) -> Colle
     return result.scalars().first()
 
 
-@router.get("/geo/vessels")
-async def get_vessels_geojson(
-    bbox: Optional[str] = Query(
-        None,
-        description="Viewport bbox as lon_min,lat_min,lon_max,lat_max",
-    ),
-    type: Optional[str] = Query(
-        None,
-        description="Comma-separated vessel types: cargo,tanker,passenger,fishing,military,other",
-    ),
-    limit: Optional[int] = Query(
-        None,
-        ge=0,
-        description="Maximum vessel features to return. Omit or pass 0 for no limit.",
-    ),
-    db: AsyncSession = Depends(get_db),
-):
-    """Return latest vessel positions as GeoJSON points."""
-    parsed_bbox = _parse_bbox(bbox)
-    requested_types = _requested_vessel_types(type)
-    merged_features, diagnostics = await _load_merged_vessel_features(db)
-    features = _filter_vessel_features(
-        merged_features,
-        bbox=parsed_bbox,
-        requested_types=requested_types,
-    )
-    if limit and limit > 0:
-        features = features[:limit]
-    return {
-        "type": "FeatureCollection",
-        "features": features,
-        "count": len(features),
-        "stats": _build_vessel_stats(features),
-        "diagnostics": {
-            **diagnostics,
-            "filtered_count": len(features),
-        },
-    }
-
-
-async def _load_merged_vessel_features(db: AsyncSession) -> tuple[list[dict[str, Any]], dict[str, Any]]:
-    aggregated_vessels = await get_aggregated_vessels(db)
+async def _load_raw_vessel_snapshot_features(
+    db: AsyncSession,
+    *,
+    bbox: tuple[float, float, float, float] | None,
+    limit: int,
+    observed_since: datetime,
+) -> tuple[list[dict[str, Any]], dict[str, Any]]:
+    if bbox is None:
+        aggregated_vessels = await get_aggregated_vessels(
+            db,
+            limit=limit,
+            observed_since=observed_since,
+        )
+    else:
+        aggregated_vessels = await get_aggregated_vessels_snapshot(
+            db,
+            bbox=bbox,
+            limit=limit,
+            observed_since=observed_since,
+        )
     raw_geojson = convert_aggregated_vessels_to_geojson(aggregated_vessels)
-
-    latest_times = (
-        select(
-            VesselPosition.mmsi.label("mmsi"),
-            func.max(VesselPosition.received_at).label("received_at"),
+    raw_features = raw_geojson.get("features", [])
+    features = raw_features
+    legacy_features: list[dict[str, Any]] = []
+    legacy_fallback_used = False
+    if not raw_features and VESSEL_SNAPSHOT_LEGACY_FALLBACK_ENABLED:
+        legacy_features = await _load_legacy_vessel_snapshot_features(
+            db,
+            bbox=bbox,
+            limit=limit,
         )
-        .group_by(VesselPosition.mmsi)
-        .subquery()
-    )
-    stmt = (
-        select(VesselPosition, VesselStatic)
-        .join(
-            latest_times,
-            (VesselPosition.mmsi == latest_times.c.mmsi)
-            & (VesselPosition.received_at == latest_times.c.received_at),
-        )
-        .outerjoin(VesselStatic, VesselStatic.mmsi == VesselPosition.mmsi)
-        .order_by(VesselPosition.received_at.desc())
-    )
+        features, _merge_diagnostics = _merge_vessel_features(raw_features, legacy_features)
+        legacy_fallback_used = bool(legacy_features)
 
-    result = await db.execute(stmt)
-    rows = list(result.all())
-    legacy_geojson = convert_vessels_to_geojson(rows)
-    merged_features, diagnostics = _merge_vessel_features(
-        raw_geojson.get("features", []),
-        legacy_geojson.get("features", []),
-    )
-    return merged_features, {
-        **diagnostics,
-        "raw_feature_count": len(raw_geojson.get("features", [])),
-        "legacy_feature_count": len(legacy_geojson.get("features", [])),
+    return features, {
+        "raw_feature_count": len(raw_features),
+        "raw_unique_mmsi": len(
+            {
+                key
+                for key in (_feature_mmsi_key(feature) for feature in raw_features)
+                if key is not None
+            }
+        ),
+        "legacy_feature_count": len(legacy_features),
+        "legacy_backfilled_mmsi": len(
+            {
+                key
+                for key in (_feature_mmsi_key(feature) for feature in legacy_features)
+                if key is not None
+            }
+        ),
+        "legacy_fallback_enabled": VESSEL_SNAPSHOT_LEGACY_FALLBACK_ENABLED,
+        "legacy_fallback_used": legacy_fallback_used,
+        "final_unique_mmsi": len(
+            {
+                key
+                for key in (_feature_mmsi_key(feature) for feature in features)
+                if key is not None
+            }
+        ),
     }
 
-
 @router.get("/vessels/custom-supplements")
 async def get_vessel_custom_supplements(db: AsyncSession = Depends(get_db)):
     """Group custom vessel_ais sources by their declared merge target for diagnostics."""
@@ -2278,7 +2621,31 @@ async def get_bgp_anomalies_geojson(
     status: Optional[str] = Query("active"),
     limit: int = Query(200, ge=1, le=1000),
     db: AsyncSession = Depends(get_db),
+    response: Response = None,
 ):
+    async def build_payload() -> dict[str, Any]:
+        return await _build_bgp_anomalies_geojson(
+            severity=severity,
+            status=status,
+            limit=limit,
+            db=db,
+        )
+
+    return await get_or_build_layer_payload(
+        key=earth_layer_cache.key("bgp-anomalies", severity=severity or "all", status=status or "all", limit=limit),
+        policy=BGP_EVENT_CACHE_POLICY,
+        builder=build_payload,
+        response=response,
+    )
+
+
+async def _build_bgp_anomalies_geojson(
+    *,
+    severity: str | None,
+    status: str | None,
+    limit: int,
+    db: AsyncSession,
+) -> dict[str, Any]:
     stmt = select(BGPAnomaly).order_by(BGPAnomaly.created_at.desc()).limit(limit)
     if severity:
         stmt = stmt.where(BGPAnomaly.severity == severity)
@@ -2298,7 +2665,31 @@ async def get_bgp_incidents_geojson(
     status: Optional[str] = Query("active"),
     limit: int = Query(100, ge=1, le=500),
     db: AsyncSession = Depends(get_db),
+    response: Response = None,
 ):
+    async def build_payload() -> dict[str, Any]:
+        return await _build_bgp_incidents_geojson(
+            severity=severity,
+            status=status,
+            limit=limit,
+            db=db,
+        )
+
+    return await get_or_build_layer_payload(
+        key=earth_layer_cache.key("bgp-incidents", severity=severity or "all", status=status or "all", limit=limit),
+        policy=BGP_EVENT_CACHE_POLICY,
+        builder=build_payload,
+        response=response,
+    )
+
+
+async def _build_bgp_incidents_geojson(
+    *,
+    severity: str | None,
+    status: str | None,
+    limit: int,
+    db: AsyncSession,
+) -> dict[str, Any]:
     stmt = select(BGPIncident).order_by(BGPIncident.created_at.desc()).limit(limit)
     if severity:
         stmt = stmt.where(BGPIncident.severity == severity)
@@ -2313,11 +2704,25 @@ async def get_bgp_incidents_geojson(
 
 
 @router.get("/geo/bgp-collectors")
-async def get_bgp_collectors_geojson(db: AsyncSession = Depends(get_db)):
+async def get_bgp_collectors_geojson(db: AsyncSession = Depends(get_db), response: Response = None):
+    async def build_payload() -> dict[str, Any]:
+        return await _build_bgp_collectors_geojson(db)
+
+    return await get_or_build_layer_payload(
+        key=earth_layer_cache.key("bgp-collectors"),
+        policy=BGP_CACHE_POLICY,
+        builder=build_payload,
+        response=response,
+    )
+
+
+async def _build_bgp_collectors_geojson(db: AsyncSession) -> dict[str, Any]:
     coverage = await build_bgp_collector_coverage(
         db,
         source_filter=("ris_live_bgp", "bgpstream_bgp"),
     )
+    if not any(int(item.get("observation_count") or 0) > 0 for item in coverage):
+        return {"type": "FeatureCollection", "features": [], "count": 0}
     coverage_by_collector = {
         item["collector"]: item
         for item in coverage
@@ -2328,8 +2733,20 @@ async def get_bgp_collectors_geojson(db: AsyncSession = Depends(get_db)):
 
 
 @router.get("/geo/summary")
-async def get_visualization_geo_summary(db: AsyncSession = Depends(get_db)):
+async def get_visualization_geo_summary(db: AsyncSession = Depends(get_db), response: Response = None):
     """Return lightweight Earth HUD counts without loading layer GeoJSON payloads."""
+    async def build_payload() -> dict[str, Any]:
+        return await _build_visualization_geo_summary(db)
+
+    return await get_or_build_layer_payload(
+        key=earth_layer_cache.key("summary"),
+        policy=SUMMARY_CACHE_POLICY,
+        builder=build_payload,
+        response=response,
+    )
+
+
+async def _build_visualization_geo_summary(db: AsyncSession) -> dict[str, Any]:
     cable_count = await _count_current_or_latest_task_data(db, "arcgis_cables")
     landing_point_count = await _count_current_or_latest_task_data(db, "arcgis_landing_points")
     satellite_count = await _count_current_or_latest_task_data(
@@ -2375,7 +2792,12 @@ async def get_visualization_geo_summary(db: AsyncSession = Depends(get_db)):
         select(func.count(func.distinct(VesselPosition.mmsi)))
     )
     legacy_unique_mmsi = int(legacy_unique_result.scalar() or 0)
-    vessel_count = max(raw_unique_mmsi, legacy_unique_mmsi)
+    legacy_fallback_active = (
+        VESSEL_SNAPSHOT_LEGACY_FALLBACK_ENABLED
+        and raw_unique_mmsi == 0
+        and legacy_unique_mmsi > 0
+    )
+    vessel_count = legacy_unique_mmsi if legacy_fallback_active else raw_unique_mmsi
     aisstream_health = await db.get(AISSourceHealth, "aisstream_vessels")
 
     return {
@@ -2386,6 +2808,8 @@ async def get_visualization_geo_summary(db: AsyncSession = Depends(get_db)):
             "satellite_count": satellite_count,
             "compute_center_count": compute_center_count,
             "vessel_count": vessel_count,
+            "vessel_count_source": "legacy_fallback" if legacy_fallback_active else "raw_recent",
+            "vessel_legacy_fallback_enabled": VESSEL_SNAPSHOT_LEGACY_FALLBACK_ENABLED,
             "vessel_raw_unique_mmsi": raw_unique_mmsi,
             "vessel_raw_unique_window_hours": raw_unique_window_hours,
             "vessel_legacy_unique_mmsi": legacy_unique_mmsi,

backend/app/api/v1/websocket.py

@@ -1,7 +1,6 @@
 """WebSocket API endpoints"""
 
 import asyncio
-import json
 from datetime import UTC, datetime
 from typing import Optional
 
@@ -15,6 +14,7 @@ from app.core.websocket.manager import manager
 
 logger = get_logger(__name__, service="api")
 router = APIRouter()
+EARTH_UPDATES_CHANNEL = "earth_updates"
 
 
 async def authenticate_token(token: str) -> Optional[dict]:
@@ -59,7 +59,7 @@ async def websocket_endpoint(
 
     is_anonymous = payload is None
     user_id = str(payload.get("sub")) if payload else f"anonymous:{id(websocket)}"
-    supported_channels = ["vessels"] if is_anonymous else [
+    supported_channels = ["vessels", "earth_news", EARTH_UPDATES_CHANNEL] if is_anonymous else [
         "gpu_clusters",
         "submarine_cables",
         "ixp_nodes",
@@ -67,6 +67,8 @@ async def websocket_endpoint(
         "dashboard",
         "datasource_tasks",
         "vessels",
+        "earth_news",
+        EARTH_UPDATES_CHANNEL,
     ]
     await manager.connect(websocket, user_id)
 
@@ -95,14 +97,44 @@ async def websocket_endpoint(
                         }
                     )
                 elif data.get("type") == "subscribe":
-                    channels = data.get("data", {}).get("channels", [])
+                    payload_data = data.get("data", {})
+                    if not isinstance(payload_data, dict):
+                        payload_data = {}
+                    channels = payload_data.get("channels", [])
+                    if isinstance(channels, str):
+                        channels = [channels]
+                    elif not isinstance(channels, list):
+                        channels = []
+                    channel = payload_data.get("channel")
+                    if channel and channel not in channels:
+                        channels = [*channels, channel]
                     if is_anonymous:
                         channels = [channel for channel in channels if channel in supported_channels]
+                    vessel_subscription = None
+                    if "vessels" in channels and "bbox" in payload_data:
+                        try:
+                            vessel_subscription = manager.subscribe_vessels(websocket, payload_data)
+                        except ValueError as exc:
+                            await websocket.send_json(
+                                {
+                                    "type": "subscription_error",
+                                    "data": {"channel": "vessels", "detail": str(exc)},
+                                }
+                            )
+                            continue
+                        channels = [channel for channel in channels if channel != "vessels"]
                     manager.subscribe(websocket, channels)
                     await websocket.send_json(
                         {
                             "type": "subscription_confirmed",
-                            "data": {"action": "subscribe", "channels": channels},
+                            "data": {
+                                "action": "subscribe",
+                                "channels": [
+                                    *channels,
+                                    *(["vessels"] if vessel_subscription else []),
+                                ],
+                                "vessels": vessel_subscription,
+                            },
                         }
                     )
                 elif data.get("type") == "unsubscribe":

backend/app/core/datasource_defaults.py

@@ -257,6 +257,16 @@ DEFAULT_DATASOURCES = {
         "credential_provider": "aisstream",
         "credential_status": "supported",
     },
+    "media_news_archive": {
+        "id": 33,
+        "name": "Media News Archive",
+        "display_name": "媒体新闻归档",
+        "module": "L4",
+        "priority": "P2",
+        "frequency_minutes": 720,
+        "is_free": True,
+        "requires_credentials": False,
+    },
 }
 
 ID_TO_COLLECTOR = {info["id"]: name for name, info in DEFAULT_DATASOURCES.items()}

backend/app/core/websocket/broadcaster.py

@@ -2,12 +2,14 @@
 
 import asyncio
 from datetime import UTC, datetime
-from typing import Dict, Any, Optional
+from typing import Dict, Any
 
 from app.core.time import to_iso8601_utc
 from app.core.websocket.manager import manager
 
 
+EARTH_UPDATES_CHANNEL = "earth_updates"
+
 
 class DataBroadcaster:
     """Periodically broadcasts data to connected WebSocket clients"""
@@ -15,6 +17,8 @@ class DataBroadcaster:
     def __init__(self):
         self.running = False
         self.tasks: Dict[str, asyncio.Task] = {}
+        self._pending_vessel_updates: Dict[str, Dict[str, Any]] = {}
+        self._vessel_flush_interval = 1.0
 
     async def get_dashboard_stats(self) -> Dict[str, Any]:
         """Get dashboard statistics"""
@@ -68,6 +72,9 @@ class DataBroadcaster:
 
     async def broadcast_custom(self, channel: str, data: Dict[str, Any]):
         """Broadcast custom data to a specific channel"""
+        if channel == "vessels":
+            self.enqueue_vessel_update(data)
+            return
         await manager.broadcast(
             {
                 "type": "data_frame",
@@ -78,6 +85,62 @@ class DataBroadcaster:
             channel=channel,
         )
 
+    async def broadcast_earth_update(self, data: Dict[str, Any]):
+        """Broadcast Earth visualization refresh hints to connected clients."""
+        await self.broadcast_custom(EARTH_UPDATES_CHANNEL, data)
+
+    def enqueue_vessel_update(self, data: Dict[str, Any]):
+        vessels = data.get("vessels") if isinstance(data, dict) else None
+        if not isinstance(vessels, list):
+            return
+        source = data.get("source")
+        action = data.get("action") or "upsert"
+        created = data.get("created")
+        for vessel in vessels:
+            if not isinstance(vessel, dict):
+                continue
+            mmsi = vessel.get("mmsi")
+            if mmsi in (None, ""):
+                continue
+            self._pending_vessel_updates[str(mmsi)] = {
+                **vessel,
+                "_source": source,
+                "_action": action,
+                "_created": created,
+            }
+
+    async def flush_vessel_updates(self):
+        if not self._pending_vessel_updates:
+            return
+        pending = self._pending_vessel_updates
+        self._pending_vessel_updates = {}
+        vessels = []
+        for item in pending.values():
+            vessel = dict(item)
+            source = vessel.pop("_source", None)
+            action = vessel.pop("_action", "upsert")
+            created = vessel.pop("_created", None)
+            vessel["source"] = source
+            vessel["action"] = action
+            vessel["created"] = created
+            vessels.append(vessel)
+        await manager.broadcast_vessels(
+            {
+                "action": "upsert",
+                "source": "mixed",
+                "created": None,
+                "vessels": vessels,
+            }
+        )
+
+    async def broadcast_vessels_periodically(self):
+        while self.running:
+            try:
+                await self.flush_vessel_updates()
+            except Exception:
+                pass
+            await asyncio.sleep(self._vessel_flush_interval)
+
     async def broadcast_datasource_task_update(self, data: Dict[str, Any]):
         """Broadcast datasource task progress updates to connected clients."""
         await manager.broadcast(
@@ -87,7 +150,7 @@ class DataBroadcaster:
                 "timestamp": to_iso8601_utc(datetime.now(UTC)),
                 "payload": data,
             },
-            channel="all",
+            channel="datasource_tasks",
         )
 
     def start(self):
@@ -95,6 +158,7 @@ class DataBroadcaster:
         if not self.running:
             self.running = True
             self.tasks["dashboard"] = asyncio.create_task(self.broadcast_stats(5))
+            self.tasks["vessels"] = asyncio.create_task(self.broadcast_vessels_periodically())
 
     def stop(self):
         """Stop all broadcasters"""
@@ -102,6 +166,7 @@ class DataBroadcaster:
         for task in self.tasks.values():
             task.cancel()
         self.tasks.clear()
+        self._pending_vessel_updates.clear()
 
 
 broadcaster = DataBroadcaster()

backend/app/core/websocket/manager.py

@@ -1,11 +1,16 @@
 """WebSocket Connection Manager"""
 
-from typing import Dict, Set, Optional
+from datetime import UTC, datetime
+from typing import Any, Dict, Set, Optional
 from fastapi import WebSocket
 import redis.asyncio as redis
 
 from app.core.config import settings
 
+MAX_VESSEL_SUBSCRIPTION_LIMIT = 5000
+MAX_VESSEL_WS_MESSAGE_ITEMS = 1000
+MAX_VESSEL_BBOX_AREA = 2500.0
+
 
 class ConnectionManager:
     """Manages WebSocket connections"""
@@ -14,6 +19,7 @@ class ConnectionManager:
         self.active_connections: Dict[str, Set[WebSocket]] = {}  # user_id -> connections
         self.channel_subscriptions: Dict[str, Set[WebSocket]] = {}
         self.websocket_channels: Dict[WebSocket, Set[str]] = {}
+        self.vessel_subscriptions: Dict[WebSocket, dict[str, Any]] = {}
         self.redis_client: Optional[redis.Redis] = None
 
     async def connect(self, websocket: WebSocket, user_id: str):
@@ -72,6 +78,50 @@ class ConnectionManager:
         channels = list(self.websocket_channels.get(websocket, set()))
         if channels:
             self.unsubscribe(websocket, channels)
+        self.vessel_subscriptions.pop(websocket, None)
+
+    def subscribe_vessels(self, websocket: WebSocket, config: dict[str, Any]) -> dict[str, Any]:
+        subscription = self._normalize_vessel_subscription(config)
+        self.channel_subscriptions.setdefault("vessels", set()).add(websocket)
+        self.websocket_channels.setdefault(websocket, set()).add("vessels")
+        self.vessel_subscriptions[websocket] = subscription
+        return subscription
+
+    def _normalize_vessel_subscription(self, config: dict[str, Any]) -> dict[str, Any]:
+        bbox = config.get("bbox")
+        if not isinstance(bbox, (list, tuple)) or len(bbox) != 4:
+            raise ValueError("vessels subscription requires bbox=[lon_min,lat_min,lon_max,lat_max]")
+        try:
+            lon_min, lat_min, lon_max, lat_max = [float(value) for value in bbox]
+        except (TypeError, ValueError) as exc:
+            raise ValueError("bbox values must be numbers") from exc
+        if lat_min > lat_max:
+            lat_min, lat_max = lat_max, lat_min
+        if lon_min > lon_max:
+            lon_min, lon_max = lon_max, lon_min
+        if not (-180 <= lon_min <= 180 and -180 <= lon_max <= 180):
+            raise ValueError("bbox longitude values must be between -180 and 180")
+        if not (-90 <= lat_min <= 90 and -90 <= lat_max <= 90):
+            raise ValueError("bbox latitude values must be between -90 and 90")
+        if (lon_max - lon_min) * (lat_max - lat_min) > MAX_VESSEL_BBOX_AREA:
+            raise ValueError("bbox is too large; zoom in or request a smaller viewport")
+
+        zoom = int(config.get("zoom") or 1)
+        if zoom < 1 or zoom > 20:
+            raise ValueError("zoom must be between 1 and 20")
+        limit = min(max(int(config.get("limit") or 1000), 1), MAX_VESSEL_SUBSCRIPTION_LIMIT)
+        vessel_types = {
+            str(item).strip().lower()
+            for item in str(config.get("type") or "").split(",")
+            if str(item).strip()
+        }
+        return {
+            "bbox": (lon_min, lat_min, lon_max, lat_max),
+            "zoom": zoom,
+            "limit": limit,
+            "type": vessel_types,
+            "last_sent_at": None,
+        }
 
     async def send_personal_message(self, message: dict, user_id: str):
         if user_id in self.active_connections:
@@ -92,6 +142,58 @@ class ConnectionManager:
                 except Exception:
                     self.unsubscribe_all(connection)
 
+    async def broadcast_vessels(self, data: dict[str, Any]):
+        vessels = data.get("vessels") if isinstance(data, dict) else None
+        if not isinstance(vessels, list) or not vessels:
+            return
+
+        for connection, subscription in list(self.vessel_subscriptions.items()):
+            matched = [
+                vessel
+                for vessel in vessels
+                if self._vessel_matches_subscription(vessel, subscription)
+            ][: min(subscription["limit"], MAX_VESSEL_WS_MESSAGE_ITEMS)]
+            if not matched:
+                continue
+            subscription["last_sent_at"] = datetime.now(UTC)
+            message = {
+                "type": "data_frame",
+                "channel": "vessels",
+                "timestamp": subscription["last_sent_at"].isoformat(),
+                "payload": {
+                    **data,
+                    "vessels": matched,
+                    "subscription": {
+                        "bbox": list(subscription["bbox"]),
+                        "zoom": subscription["zoom"],
+                        "limit": subscription["limit"],
+                    },
+                },
+            }
+            try:
+                await connection.send_json(message)
+            except Exception:
+                self.unsubscribe_all(connection)
+
+    def _vessel_matches_subscription(
+        self,
+        vessel: dict[str, Any],
+        subscription: dict[str, Any],
+    ) -> bool:
+        try:
+            lon = float(vessel.get("lon"))
+            lat = float(vessel.get("lat"))
+        except (TypeError, ValueError):
+            return False
+        lon_min, lat_min, lon_max, lat_max = subscription["bbox"]
+        if not (lon_min <= lon <= lon_max and lat_min <= lat <= lat_max):
+            return False
+        requested_types = subscription.get("type") or set()
+        if not requested_types:
+            return True
+        type_name = str(vessel.get("vessel_type_name") or "").lower()
+        return any(requested_type in type_name for requested_type in requested_types)
+
     async def close_all(self):
         for user_id in self.active_connections:
             for connection in self.active_connections[user_id]:
@@ -99,6 +201,7 @@ class ConnectionManager:
         self.active_connections.clear()
         self.channel_subscriptions.clear()
         self.websocket_channels.clear()
+        self.vessel_subscriptions.clear()
 
 
 manager = ConnectionManager()

backend/app/db/session.py

@@ -1,6 +1,6 @@
 from typing import AsyncGenerator
 
-from sqlalchemy import text
+from sqlalchemy import bindparam, text
 from sqlalchemy.ext.asyncio import AsyncSession, create_async_engine, async_sessionmaker
 from sqlalchemy.orm import declarative_base
 
@@ -72,25 +72,112 @@ async def seed_default_datasources(session: AsyncSession):
     await session.commit()
 
 
+LEGACY_EARTH_BOUNDARY_SOURCES = (
+    "earth_admin0_boundaries",
+    "earth_coastline",
+    "earth_claim_lines",
+    "earth_boundary_tiles",
+)
+LEGACY_EARTH_BOUNDARY_DATATYPES = (
+    "earth_boundary_source",
+    "earth_boundary_tiles",
+)
+LEGACY_EARTH_BOUNDARY_IDS = (29, 30, 31, 32)
+
+
+async def purge_legacy_earth_boundary_datasources(session: AsyncSession) -> None:
+    source_names = tuple(LEGACY_EARTH_BOUNDARY_SOURCES)
+    source_ids = tuple(LEGACY_EARTH_BOUNDARY_IDS)
+    data_types = tuple(LEGACY_EARTH_BOUNDARY_DATATYPES)
+    await session.execute(
+        text(
+            """
+            DELETE FROM datasource_mapping_templates
+            WHERE target_schema IN :data_types
+               OR datasource_config_id IN (
+                    SELECT id FROM datasource_configs WHERE name IN :source_names
+               )
+            """
+        ).bindparams(bindparam("source_names", expanding=True), bindparam("data_types", expanding=True)),
+        {"source_names": list(source_names), "data_types": list(data_types)},
+    )
+    await session.execute(
+        text("DELETE FROM datasource_configs WHERE name IN :source_names").bindparams(
+            bindparam("source_names", expanding=True)
+        ),
+        {"source_names": list(source_names)},
+    )
+    await session.execute(
+        text(
+            """
+            DELETE FROM collected_data
+            WHERE source IN :source_names OR data_type IN :data_types
+            """
+        ).bindparams(bindparam("source_names", expanding=True), bindparam("data_types", expanding=True)),
+        {"source_names": list(source_names), "data_types": list(data_types)},
+    )
+    await session.execute(
+        text(
+            """
+            DELETE FROM data_snapshots
+            WHERE source IN :source_names OR datasource_id IN :source_ids
+            """
+        ).bindparams(bindparam("source_names", expanding=True), bindparam("source_ids", expanding=True)),
+        {"source_names": list(source_names), "source_ids": list(source_ids)},
+    )
+    await session.execute(
+        text("DELETE FROM collection_tasks WHERE datasource_id IN :source_ids").bindparams(
+            bindparam("source_ids", expanding=True)
+        ),
+        {"source_ids": list(source_ids)},
+    )
+    await session.execute(
+        text("DELETE FROM data_sources WHERE source IN :source_names OR id IN :source_ids").bindparams(
+            bindparam("source_names", expanding=True), bindparam("source_ids", expanding=True)
+        ),
+        {"source_names": list(source_names), "source_ids": list(source_ids)},
+    )
+    await session.commit()
+
+
+DEFAULT_LOGIN_USERS = (
+    {
+        "username": "admin",
+        "email": "admin@planet.local",
+        "password": "admin123",
+        "role": "super_admin",
+    },
+    {
+        "username": "linkong",
+        "email": "linkong@planet.local",
+        "password": "LK12345678",
+        "role": "super_admin",
+    },
+)
+
+
 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,
+    for default_user in DEFAULT_LOGIN_USERS:
+        result = await session.execute(
+            text("SELECT id FROM users WHERE username = :username"),
+            {"username": default_user["username"]},
+        )
+        if result.fetchone():
+            continue
+
+        session.add(
+            User(
+                username=default_user["username"],
+                email=default_user["email"],
+                password_hash=get_password_hash(default_user["password"]),
+                role=default_user["role"],
+                is_active=True,
+                email_verified=True,
+            )
         )
-    )
     await session.commit()
 
 
@@ -115,6 +202,8 @@ async def init_db():
     import app.models.vessel  # noqa: F401
     import app.models.vessel_enrichment  # noqa: F401
     import app.models.datasource_mapping  # noqa: F401
+    import app.models.earth_news  # noqa: F401
+    import app.models.earth_interactable  # noqa: F401
 
     logger.warning_event(
         "Database pool settings active",
@@ -130,14 +219,31 @@ async def init_db():
 
     async with engine.begin() as conn:
         await conn.run_sync(Base.metadata.create_all)
+        users_email_verified_existed = (
+            await conn.execute(
+                text(
+                    """
+                    SELECT 1
+                    FROM information_schema.columns
+                    WHERE table_name = 'users' AND column_name = 'email_verified'
+                    """
+                )
+            )
+        ).fetchone() is not None
         await conn.execute(
             text(
                 """
                 ALTER TABLE users
-                ADD COLUMN IF NOT EXISTS gatekeeper_groups JSONB DEFAULT '[]'::jsonb
+                ADD COLUMN IF NOT EXISTS gatekeeper_groups JSONB DEFAULT '[]'::jsonb,
+                ADD COLUMN IF NOT EXISTS email_verified BOOLEAN NOT NULL DEFAULT FALSE,
+                ADD COLUMN IF NOT EXISTS pending_email VARCHAR(255)
                 """
             )
         )
+        if not users_email_verified_existed:
+            await conn.execute(
+                text("UPDATE users SET email_verified = TRUE WHERE email_verified = FALSE")
+            )
         await conn.execute(
             text(
                 """
@@ -153,6 +259,406 @@ async def init_db():
                 """
             )
         )
+        await conn.execute(
+            text(
+                """
+                CREATE TABLE IF NOT EXISTS earth_data_change_events (
+                    id BIGSERIAL PRIMARY KEY,
+                    table_name VARCHAR(128) NOT NULL,
+                    operation VARCHAR(16) NOT NULL,
+                    source VARCHAR(128),
+                    entity_key VARCHAR(255),
+                    payload JSONB NOT NULL,
+                    occurred_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+                    consumed_at TIMESTAMPTZ
+                )
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                CREATE INDEX IF NOT EXISTS idx_earth_data_change_events_unconsumed
+                ON earth_data_change_events (consumed_at, id)
+                WHERE consumed_at IS NULL
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                CREATE OR REPLACE FUNCTION planet_emit_earth_data_changed_statement(
+                    change_table TEXT,
+                    change_operation TEXT,
+                    change_source TEXT,
+                    source_record_count INTEGER,
+                    source_entity_keys TEXT[]
+                )
+                RETURNS VOID AS $$
+                DECLARE
+                    change_event_id BIGINT;
+                    change_payload JSONB;
+                BEGIN
+                    change_payload := jsonb_build_object(
+                        'event', 'earth.layer.changed',
+                        'table', change_table,
+                        'operation', change_operation,
+                        'source', change_source,
+                        'entity_key', NULL,
+                        'entity_keys', COALESCE(to_jsonb(source_entity_keys), '[]'::jsonb),
+                        'records_processed', COALESCE(source_record_count, 0),
+                        'occurred_at', NOW()
+                    );
+
+                    INSERT INTO earth_data_change_events (
+                        table_name,
+                        operation,
+                        source,
+                        entity_key,
+                        payload,
+                        occurred_at
+                    ) VALUES (
+                        change_table,
+                        change_operation,
+                        change_source,
+                        NULL,
+                        change_payload,
+                        NOW()
+                    )
+                    RETURNING id INTO change_event_id;
+
+                    change_payload := change_payload || jsonb_build_object(
+                        'event_id', change_event_id
+                    );
+
+                    UPDATE earth_data_change_events
+                    SET payload = change_payload
+                    WHERE id = change_event_id;
+
+                    PERFORM pg_notify(
+                        'planet_earth_data_changes',
+                        change_payload::text
+                    );
+                END;
+                $$ LANGUAGE plpgsql;
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                CREATE OR REPLACE FUNCTION planet_emit_collected_data_changed_statement(
+                    change_operation TEXT,
+                    change_source TEXT,
+                    source_record_count INTEGER,
+                    source_entity_keys TEXT[]
+                )
+                RETURNS VOID AS $$
+                BEGIN
+                    PERFORM planet_emit_earth_data_changed_statement(
+                        'collected_data',
+                        change_operation,
+                        change_source,
+                        source_record_count,
+                        source_entity_keys
+                    );
+                END;
+                $$ LANGUAGE plpgsql;
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                CREATE OR REPLACE FUNCTION planet_notify_earth_table_changed_statement()
+                RETURNS trigger AS $$
+                DECLARE
+                    change_source TEXT;
+                    source_record_count INTEGER;
+                    source_entity_keys TEXT[];
+                BEGIN
+                    IF TG_OP = 'INSERT' THEN
+                        FOR change_source IN
+                            SELECT DISTINCT COALESCE(NULLIF(row_data->>'source', ''), TG_TABLE_NAME)
+                            FROM (SELECT to_jsonb(t) AS row_data FROM new_rows AS t) changed_rows
+                        LOOP
+                            SELECT
+                                COUNT(*),
+                                ARRAY(
+                                    SELECT DISTINCT COALESCE(
+                                        NULLIF(row_data->>'entity_key', ''),
+                                        NULLIF(row_data->>'source_id', ''),
+                                        NULLIF(row_data->>'incident_key', ''),
+                                        NULLIF(row_data->>'id', ''),
+                                        NULLIF(row_data->>'mmsi', '')
+                                    )
+                                    FROM (SELECT to_jsonb(t) AS row_data FROM new_rows AS t) rows_for_keys
+                                    WHERE COALESCE(NULLIF(row_data->>'source', ''), TG_TABLE_NAME) = change_source
+                                    LIMIT 20
+                                )
+                            INTO source_record_count, source_entity_keys
+                            FROM (SELECT to_jsonb(t) AS row_data FROM new_rows AS t) rows_for_count
+                            WHERE COALESCE(NULLIF(row_data->>'source', ''), TG_TABLE_NAME) = change_source;
+
+                            PERFORM planet_emit_earth_data_changed_statement(
+                                TG_TABLE_NAME,
+                                TG_OP,
+                                change_source,
+                                source_record_count,
+                                source_entity_keys
+                            );
+                        END LOOP;
+                    ELSIF TG_OP = 'DELETE' THEN
+                        FOR change_source IN
+                            SELECT DISTINCT COALESCE(NULLIF(row_data->>'source', ''), TG_TABLE_NAME)
+                            FROM (SELECT to_jsonb(t) AS row_data FROM old_rows AS t) changed_rows
+                        LOOP
+                            SELECT
+                                COUNT(*),
+                                ARRAY(
+                                    SELECT DISTINCT COALESCE(
+                                        NULLIF(row_data->>'entity_key', ''),
+                                        NULLIF(row_data->>'source_id', ''),
+                                        NULLIF(row_data->>'incident_key', ''),
+                                        NULLIF(row_data->>'id', ''),
+                                        NULLIF(row_data->>'mmsi', '')
+                                    )
+                                    FROM (SELECT to_jsonb(t) AS row_data FROM old_rows AS t) rows_for_keys
+                                    WHERE COALESCE(NULLIF(row_data->>'source', ''), TG_TABLE_NAME) = change_source
+                                    LIMIT 20
+                                )
+                            INTO source_record_count, source_entity_keys
+                            FROM (SELECT to_jsonb(t) AS row_data FROM old_rows AS t) rows_for_count
+                            WHERE COALESCE(NULLIF(row_data->>'source', ''), TG_TABLE_NAME) = change_source;
+
+                            PERFORM planet_emit_earth_data_changed_statement(
+                                TG_TABLE_NAME,
+                                TG_OP,
+                                change_source,
+                                source_record_count,
+                                source_entity_keys
+                            );
+                        END LOOP;
+                    ELSIF TG_OP = 'UPDATE' THEN
+                        FOR change_source IN
+                            SELECT DISTINCT COALESCE(NULLIF(row_data->>'source', ''), TG_TABLE_NAME)
+                            FROM (
+                                SELECT to_jsonb(t) AS row_data FROM new_rows AS t
+                                UNION ALL
+                                SELECT to_jsonb(t) AS row_data FROM old_rows AS t
+                            ) changed_rows
+                        LOOP
+                            SELECT
+                                COUNT(*),
+                                ARRAY(
+                                    SELECT DISTINCT COALESCE(
+                                        NULLIF(row_data->>'entity_key', ''),
+                                        NULLIF(row_data->>'source_id', ''),
+                                        NULLIF(row_data->>'incident_key', ''),
+                                        NULLIF(row_data->>'id', ''),
+                                        NULLIF(row_data->>'mmsi', '')
+                                    )
+                                    FROM (
+                                        SELECT to_jsonb(t) AS row_data FROM new_rows AS t
+                                        UNION ALL
+                                        SELECT to_jsonb(t) AS row_data FROM old_rows AS t
+                                    ) rows_for_keys
+                                    WHERE COALESCE(NULLIF(row_data->>'source', ''), TG_TABLE_NAME) = change_source
+                                    LIMIT 20
+                                )
+                            INTO source_record_count, source_entity_keys
+                            FROM (
+                                SELECT to_jsonb(t) AS row_data FROM new_rows AS t
+                                UNION ALL
+                                SELECT to_jsonb(t) AS row_data FROM old_rows AS t
+                            ) rows_for_count
+                            WHERE COALESCE(NULLIF(row_data->>'source', ''), TG_TABLE_NAME) = change_source;
+
+                            PERFORM planet_emit_earth_data_changed_statement(
+                                TG_TABLE_NAME,
+                                TG_OP,
+                                change_source,
+                                source_record_count,
+                                source_entity_keys
+                            );
+                        END LOOP;
+                    END IF;
+
+                    RETURN NULL;
+                END;
+                $$ LANGUAGE plpgsql;
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                CREATE OR REPLACE FUNCTION planet_notify_collected_data_changed_statement()
+                RETURNS trigger AS $$
+                DECLARE
+                    change_source TEXT;
+                    source_record_count INTEGER;
+                    source_entity_keys TEXT[];
+                BEGIN
+                    IF TG_OP = 'INSERT' THEN
+                        FOR change_source IN
+                            SELECT DISTINCT source FROM new_rows WHERE source IS NOT NULL
+                        LOOP
+                            SELECT
+                                COUNT(*),
+                                ARRAY(
+                                    SELECT DISTINCT COALESCE(entity_key, source_id, id::text)
+                                    FROM new_rows
+                                    WHERE source = change_source
+                                    LIMIT 20
+                                )
+                            INTO source_record_count, source_entity_keys
+                            FROM new_rows
+                            WHERE source = change_source;
+
+                            PERFORM planet_emit_collected_data_changed_statement(
+                                TG_OP,
+                                change_source,
+                                source_record_count,
+                                source_entity_keys
+                            );
+                        END LOOP;
+                    ELSIF TG_OP = 'DELETE' THEN
+                        FOR change_source IN
+                            SELECT DISTINCT source FROM old_rows WHERE source IS NOT NULL
+                        LOOP
+                            SELECT
+                                COUNT(*),
+                                ARRAY(
+                                    SELECT DISTINCT COALESCE(entity_key, source_id, id::text)
+                                    FROM old_rows
+                                    WHERE source = change_source
+                                    LIMIT 20
+                                )
+                            INTO source_record_count, source_entity_keys
+                            FROM old_rows
+                            WHERE source = change_source;
+
+                            PERFORM planet_emit_collected_data_changed_statement(
+                                TG_OP,
+                                change_source,
+                                source_record_count,
+                                source_entity_keys
+                            );
+                        END LOOP;
+                    ELSIF TG_OP = 'UPDATE' THEN
+                        FOR change_source IN
+                            SELECT DISTINCT source FROM (
+                                SELECT source FROM new_rows
+                                UNION
+                                SELECT source FROM old_rows
+                            ) changed_sources
+                            WHERE source IS NOT NULL
+                        LOOP
+                            SELECT
+                                COUNT(*),
+                                ARRAY(
+                                    SELECT DISTINCT COALESCE(entity_key, source_id, id::text)
+                                    FROM (
+                                        SELECT id, source_id, entity_key, source FROM new_rows
+                                        UNION ALL
+                                        SELECT id, source_id, entity_key, source FROM old_rows
+                                    ) changed_rows
+                                    WHERE source = change_source
+                                    LIMIT 20
+                                )
+                            INTO source_record_count, source_entity_keys
+                            FROM (
+                                SELECT id, source_id, entity_key, source FROM new_rows
+                                UNION ALL
+                                SELECT id, source_id, entity_key, source FROM old_rows
+                            ) changed_rows
+                            WHERE source = change_source;
+
+                            PERFORM planet_emit_collected_data_changed_statement(
+                                TG_OP,
+                                change_source,
+                                source_record_count,
+                                source_entity_keys
+                            );
+                        END LOOP;
+                    END IF;
+
+                    RETURN NULL;
+                END;
+                $$ LANGUAGE plpgsql;
+                """
+            )
+        )
+        for statement in (
+            "DROP TRIGGER IF EXISTS tr_planet_collected_data_changed ON collected_data",
+            "DROP TRIGGER IF EXISTS tr_planet_collected_data_changed_insert ON collected_data",
+            "DROP TRIGGER IF EXISTS tr_planet_collected_data_changed_update ON collected_data",
+            "DROP TRIGGER IF EXISTS tr_planet_collected_data_changed_delete ON collected_data",
+            "DROP FUNCTION IF EXISTS planet_notify_collected_data_changed()",
+            """
+            CREATE TRIGGER tr_planet_collected_data_changed_insert
+            AFTER INSERT ON collected_data
+            REFERENCING NEW TABLE AS new_rows
+            FOR EACH STATEMENT
+            EXECUTE FUNCTION planet_notify_collected_data_changed_statement()
+            """,
+            """
+            CREATE TRIGGER tr_planet_collected_data_changed_update
+            AFTER UPDATE ON collected_data
+            REFERENCING OLD TABLE AS old_rows NEW TABLE AS new_rows
+            FOR EACH STATEMENT
+            EXECUTE FUNCTION planet_notify_collected_data_changed_statement()
+            """,
+            """
+            CREATE TRIGGER tr_planet_collected_data_changed_delete
+            AFTER DELETE ON collected_data
+            REFERENCING OLD TABLE AS old_rows
+            FOR EACH STATEMENT
+            EXECUTE FUNCTION planet_notify_collected_data_changed_statement()
+            """,
+        ):
+            await conn.execute(text(statement))
+        for table_name in (
+            "bgp_observations",
+            "bgp_anomalies",
+            "bgp_incidents",
+            "bgp_collector_locations",
+            "vessel_static",
+            "vessel_position",
+            "ais_raw_observations",
+            "ais_source_health",
+            "compute_center_locations",
+            "earth_interactables",
+            "earth_news_items",
+        ):
+            for statement in (
+                f"DROP TRIGGER IF EXISTS tr_planet_{table_name}_changed_insert ON {table_name}",
+                f"DROP TRIGGER IF EXISTS tr_planet_{table_name}_changed_update ON {table_name}",
+                f"DROP TRIGGER IF EXISTS tr_planet_{table_name}_changed_delete ON {table_name}",
+                f"""
+                CREATE TRIGGER tr_planet_{table_name}_changed_insert
+                AFTER INSERT ON {table_name}
+                REFERENCING NEW TABLE AS new_rows
+                FOR EACH STATEMENT
+                EXECUTE FUNCTION planet_notify_earth_table_changed_statement()
+                """,
+                f"""
+                CREATE TRIGGER tr_planet_{table_name}_changed_update
+                AFTER UPDATE ON {table_name}
+                REFERENCING OLD TABLE AS old_rows NEW TABLE AS new_rows
+                FOR EACH STATEMENT
+                EXECUTE FUNCTION planet_notify_earth_table_changed_statement()
+                """,
+                f"""
+                CREATE TRIGGER tr_planet_{table_name}_changed_delete
+                AFTER DELETE ON {table_name}
+                REFERENCING OLD TABLE AS old_rows
+                FOR EACH STATEMENT
+                EXECUTE FUNCTION planet_notify_earth_table_changed_statement()
+                """,
+            ):
+                await conn.execute(text(statement))
         await conn.execute(
             text(
                 """
@@ -162,7 +668,39 @@ async def init_db():
                 ADD COLUMN IF NOT EXISTS phase_message VARCHAR(255),
                 ADD COLUMN IF NOT EXISTS phase_current BIGINT,
                 ADD COLUMN IF NOT EXISTS phase_total BIGINT,
-                ADD COLUMN IF NOT EXISTS phase_unit VARCHAR(30)
+                ADD COLUMN IF NOT EXISTS phase_unit VARCHAR(30),
+                ADD COLUMN IF NOT EXISTS source VARCHAR(100),
+                ADD COLUMN IF NOT EXISTS task_type VARCHAR(30) NOT NULL DEFAULT 'collect',
+                ADD COLUMN IF NOT EXISTS payload JSONB NOT NULL DEFAULT '{}'::jsonb,
+                ADD COLUMN IF NOT EXISTS rollback_policy VARCHAR(40) NOT NULL DEFAULT 'keep_committed_batches',
+                ADD COLUMN IF NOT EXISTS dedupe_key VARCHAR(180),
+                ADD COLUMN IF NOT EXISTS worker_id VARCHAR(120),
+                ADD COLUMN IF NOT EXISTS locked_at TIMESTAMPTZ,
+                ADD COLUMN IF NOT EXISTS requested_cancel_at TIMESTAMPTZ,
+                ADD COLUMN IF NOT EXISTS cancel_reason TEXT
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                ALTER TABLE earth_news_items
+                ADD COLUMN IF NOT EXISTS content_language VARCHAR(32) NOT NULL DEFAULT 'en',
+                ADD COLUMN IF NOT EXISTS localizations JSONB NOT NULL DEFAULT '{}'::jsonb,
+                ADD COLUMN IF NOT EXISTS enrichment_status VARCHAR(80) NOT NULL DEFAULT 'pending',
+                ADD COLUMN IF NOT EXISTS enrichment_error TEXT,
+                ADD COLUMN IF NOT EXISTS enriched_at TIMESTAMPTZ
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                ALTER TABLE earth_interactables
+                ADD COLUMN IF NOT EXISTS altitude DOUBLE PRECISION,
+                ADD COLUMN IF NOT EXISTS revision INTEGER NOT NULL DEFAULT 1,
+                ADD COLUMN IF NOT EXISTS is_deleted BOOLEAN NOT NULL DEFAULT FALSE,
+                ADD COLUMN IF NOT EXISTS deleted_at TIMESTAMPTZ
                 """
             )
         )
@@ -174,6 +712,64 @@ async def init_db():
                 """
             )
         )
+        await conn.execute(
+            text(
+                """
+                CREATE INDEX IF NOT EXISTS idx_earth_news_enrichment_status
+                ON earth_news_items (enrichment_status)
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                CREATE INDEX IF NOT EXISTS idx_earth_news_enriched_at
+                ON earth_news_items (enriched_at)
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                CREATE INDEX IF NOT EXISTS idx_earth_interactables_layer_deleted
+                ON earth_interactables (layer, is_deleted)
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                CREATE INDEX IF NOT EXISTS idx_earth_interactables_updated_at
+                ON earth_interactables (updated_at)
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                CREATE INDEX IF NOT EXISTS idx_collection_tasks_source_status
+                ON collection_tasks (source, status)
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                CREATE INDEX IF NOT EXISTS idx_collection_tasks_queue
+                ON collection_tasks (status, created_at, id)
+                WHERE status = 'queued'
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                CREATE INDEX IF NOT EXISTS idx_collection_tasks_dedupe
+                ON collection_tasks (dedupe_key)
+                WHERE dedupe_key IS NOT NULL
+                """
+            )
+        )
         await conn.execute(
             text(
                 """
@@ -198,6 +794,26 @@ async def init_db():
                 """
             )
         )
+        await conn.execute(
+            text(
+                """
+                CREATE INDEX IF NOT EXISTS idx_ais_raw_schema_observed_desc
+                ON ais_raw_observations (target_schema, observed_at DESC)
+                """
+            )
+        )
+        await conn.execute(
+            text(
+                """
+                CREATE INDEX IF NOT EXISTS idx_ais_raw_payload_lon_lat
+                ON ais_raw_observations (
+                    ((normalized_payload->>'lon')::double precision),
+                    ((normalized_payload->>'lat')::double precision)
+                )
+                WHERE target_schema = 'vessel_ais'
+                """
+            )
+        )
         await conn.execute(
             text(
                 """
@@ -228,4 +844,5 @@ async def init_db():
         await seed_default_bgp_collector_locations(session)
         await seed_compute_center_locations_from_source_coords(session)
         await seed_default_datasources(session)
+        await purge_legacy_earth_boundary_datasources(session)
         await ensure_default_admin_user(session)

backend/app/main.py

@@ -1,8 +1,10 @@
 from contextlib import asynccontextmanager
+from pathlib import Path
 from uuid import uuid4
 
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
+from fastapi.staticfiles import StaticFiles
 from starlette.middleware.base import BaseHTTPMiddleware
 
 from app.api.main import api_router
@@ -18,6 +20,15 @@ from app.services.scheduler import (
     stop_scheduler,
     sync_scheduler_with_datasources,
 )
+from app.services.earth_news_worker import (
+    start_earth_news_target_worker,
+    stop_earth_news_target_worker,
+)
+from app.services.earth_db_change_listener import (
+    start_earth_db_change_listener,
+    stop_earth_db_change_listener,
+)
+from app.services.data_jobs import start_data_job_worker, stop_data_job_worker
 
 
 configure_logging()
@@ -53,7 +64,13 @@ async def lifespan(app: FastAPI):
     start_scheduler()
     await sync_scheduler_with_datasources()
     broadcaster.start()
+    start_data_job_worker()
+    start_earth_db_change_listener()
+    start_earth_news_target_worker()
     yield
+    await stop_earth_news_target_worker()
+    await stop_earth_db_change_listener()
+    await stop_data_job_worker()
     broadcaster.stop()
     stop_scheduler()
 
@@ -82,6 +99,14 @@ app.add_middleware(WebSocketCORSMiddleware)
 app.include_router(api_router, prefix="/api/v1")
 app.include_router(websocket.router)
 
+EARTH_BRAND_ASSET_DIR = Path(__file__).resolve().parents[2] / "data" / "earth-brand"
+EARTH_BRAND_ASSET_DIR.mkdir(parents=True, exist_ok=True)
+app.mount(
+    "/earth-brand-assets",
+    StaticFiles(directory=str(EARTH_BRAND_ASSET_DIR)),
+    name="earth-brand-assets",
+)
+
 
 @app.get("/health")
 async def health_check():

backend/app/models/__init__.py

@@ -16,6 +16,8 @@ from app.models.playground_message import PlaygroundMessage
 from app.models.system_log import SystemLog, AuditLog
 from app.models.vessel import AISConflictRecord, AISRawObservation, AISSourceHealth, VesselPosition, VesselStatic
 from app.models.datasource_mapping import DataSourceMappingTemplate
+from app.models.earth_news import EarthNewsItem
+from app.models.earth_interactable import EarthInteractable
 
 __all__ = [
     "User",
@@ -43,4 +45,6 @@ __all__ = [
     "AISConflictRecord",
     "AISSourceHealth",
     "DataSourceMappingTemplate",
+    "EarthNewsItem",
+    "EarthInteractable",
 ]

backend/app/models/earth_interactable.py

@@ -0,0 +1,30 @@
+"""Persistent Earth interactable objects."""
+
+from sqlalchemy import Boolean, Column, DateTime, Float, Index, Integer, JSON, String, Text
+from sqlalchemy.sql import func
+
+from app.db.session import Base
+
+
+class EarthInteractable(Base):
+    __tablename__ = "earth_interactables"
+
+    id = Column(String(160), primary_key=True)
+    layer = Column(String(80), nullable=False, default="interactables", index=True)
+    kind = Column(String(80), nullable=False, default="default", index=True)
+    label = Column(String(255), nullable=False, default="")
+    description = Column(Text, nullable=False, default="")
+    latitude = Column(Float, nullable=False)
+    longitude = Column(Float, nullable=False)
+    altitude = Column(Float, nullable=True)
+    revision = Column(Integer, nullable=False, default=1)
+    properties = Column(JSON, nullable=False, default=dict)
+    is_deleted = Column(Boolean, nullable=False, default=False, index=True)
+    created_at = Column(DateTime(timezone=True), server_default=func.now(), nullable=False)
+    updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
+    deleted_at = Column(DateTime(timezone=True), nullable=True, index=True)
+
+    __table_args__ = (
+        Index("idx_earth_interactables_layer_deleted", "layer", "is_deleted"),
+        Index("idx_earth_interactables_updated_at", "updated_at"),
+    )

backend/app/models/earth_news.py

@@ -0,0 +1,40 @@
+from sqlalchemy import Boolean, Column, DateTime, Float, Index, JSON, String, Text
+from sqlalchemy.sql import func
+
+from app.db.session import Base
+
+
+class EarthNewsItem(Base):
+    __tablename__ = "earth_news_items"
+
+    id = Column(String(160), primary_key=True)
+    title = Column(String(500), nullable=False)
+    summary = Column(Text, nullable=False, default="")
+    content_language = Column(String(32), nullable=False, default="en")
+    localizations = Column(JSON, nullable=False, default=dict)
+    url = Column(Text, nullable=False)
+    source = Column(String(255), nullable=False, default="")
+    feed_name = Column(String(255), nullable=False, default="")
+    region = Column(String(80), nullable=False, index=True)
+    homepage_url = Column(Text, nullable=False, default="")
+    published_at = Column(DateTime(timezone=True), nullable=True, index=True)
+
+    latitude = Column(Float, nullable=False)
+    longitude = Column(Float, nullable=False)
+    location_label = Column(String(255), nullable=False)
+    location_source = Column(String(80), nullable=False, default="region_anchor")
+    verified = Column(Boolean, nullable=False, default=False, index=True)
+    location_meta = Column(JSON, nullable=False, default=dict)
+
+    first_seen_at = Column(DateTime(timezone=True), server_default=func.now(), nullable=False)
+    last_seen_at = Column(DateTime(timezone=True), server_default=func.now(), nullable=False, index=True)
+    resolved_at = Column(DateTime(timezone=True), nullable=True, index=True)
+    enrichment_status = Column(String(80), nullable=False, default="pending", index=True)
+    enrichment_error = Column(Text, nullable=True)
+    enriched_at = Column(DateTime(timezone=True), nullable=True, index=True)
+    updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
+
+    __table_args__ = (
+        Index("idx_earth_news_region_published", "region", "published_at"),
+        Index("idx_earth_news_region_seen", "region", "last_seen_at"),
+    )

backend/app/models/task.py

@@ -1,6 +1,6 @@
-"""Collection Task model"""
+"""Datasource job model."""
 
-from sqlalchemy import BigInteger, Column, DateTime, Integer, String, Text, Float
+from sqlalchemy import BigInteger, Column, DateTime, Float, Integer, JSON, String, Text
 from sqlalchemy.sql import func
 
 from app.db.session import Base
@@ -11,7 +11,9 @@ 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
+    source = Column(String(100), nullable=True, index=True)
+    task_type = Column(String(30), nullable=False, default="collect", index=True)
+    status = Column(String(20), nullable=False)  # queued, running, cancelling, success, failed, cancelled
     phase = Column(String(30), default="queued")
     phase_progress = Column(Float)
     phase_message = Column(String(255))
@@ -24,6 +26,13 @@ class CollectionTask(Base):
     total_records = Column(Integer, default=0)  # Total records to process
     progress = Column(Float, default=0.0)  # Progress percentage (0-100)
     error_message = Column(Text)
+    payload = Column(JSON, default=dict)
+    rollback_policy = Column(String(40), nullable=False, default="keep_committed_batches")
+    dedupe_key = Column(String(180), nullable=True, index=True)
+    worker_id = Column(String(120), nullable=True, index=True)
+    locked_at = Column(DateTime(timezone=True), nullable=True, index=True)
+    requested_cancel_at = Column(DateTime(timezone=True), nullable=True)
+    cancel_reason = Column(Text)
     created_at = Column(DateTime(timezone=True), server_default=func.now())
 
     def __repr__(self):

backend/app/models/user.py

@@ -14,6 +14,8 @@ class User(Base):
     role = Column(String(20), default="viewer")
     gatekeeper_groups = Column(JSON, default=list)
     is_active = Column(Boolean, default=True)
+    email_verified = Column(Boolean, default=False, nullable=False)
+    pending_email = Column(String(255), nullable=True)
     last_login_at = Column(DateTime(timezone=True))
     created_at = Column(DateTime(timezone=True), server_default=func.now())
     updated_at = Column(

backend/app/schemas/ai.py

@@ -13,10 +13,11 @@ class AIContentBlock(BaseModel):
 
 class SituationalAnalysisRequest(BaseModel):
     title: str = Field(..., min_length=1, max_length=200)
-    objective: str = Field(..., min_length=1, max_length=1000)
+    objective: str = Field(..., min_length=1, max_length=20000)
     context: dict[str, Any] = Field(default_factory=dict)
     observations: list[str] = Field(default_factory=list)
     constraints: list[str] = Field(default_factory=list)
+    system_prompt: str | None = Field(default=None, max_length=8000)
     preferred_model: str | None = Field(default=None, max_length=200)
     thinking: dict[str, Any] | None = None
 

backend/app/schemas/user.py

@@ -39,7 +39,34 @@ class UserResponse(UserBase):
     role: str
     gatekeeper_groups: list[str] = Field(default_factory=list)
     is_active: bool
+    email_verified: bool = False
     created_at: datetime
 
     class Config:
         from_attributes = True
+
+
+class UserRegister(BaseModel):
+    username: str = Field(..., min_length=3, max_length=50)
+    email: EmailStr
+    password: str = Field(..., min_length=8, max_length=128)
+
+
+class VerifyEmailRequest(BaseModel):
+    email: EmailStr
+    code: str = Field(..., min_length=6, max_length=6)
+
+
+class ResendCodeRequest(BaseModel):
+    email: EmailStr
+    purpose: str = Field(default="register", pattern="^(register|verify_email|reset_password)$")
+
+
+class ForgotPasswordRequest(BaseModel):
+    email: EmailStr
+
+
+class ResetPasswordRequest(BaseModel):
+    email: EmailStr
+    code: str = Field(..., min_length=6, max_length=6)
+    new_password: str = Field(..., min_length=8, max_length=128)

backend/app/services/ai_client.py

@@ -1,18 +1,25 @@
 from __future__ import annotations
 
 import asyncio
+import json
+from time import perf_counter
 
 import httpx
 from fastapi import Depends, HTTPException, status
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.core.config import settings
+from app.core.logging import get_logger
 from app.db.session import get_db
 from app.schemas.ai import (
     AIProviderStatusResponse,
     SituationalAnalysisRequest,
     SituationalAnalysisResponse,
 )
+from app.services.business_logs import emit_business_log, exception_context
+
+
+logger = get_logger(__name__, service="ai")
 
 
 class AIProviderClient:
@@ -57,10 +64,25 @@ class AIProviderClient:
             value = self.llm_config.get(key)
             if value not in (None, ""):
                 headers[header_name] = str(value)
+        model_provider_apis = self.llm_config.get("model_provider_apis")
+        if isinstance(model_provider_apis, dict) and model_provider_apis:
+            headers["X-AI-Model-Provider-APIs"] = json.dumps(model_provider_apis)
         return headers
 
     async def get_status(self, request_id: str | None = None) -> AIProviderStatusResponse:
+        context = self._base_log_context(operation="status")
         if not self.service_url:
+            await emit_business_log(
+                logger,
+                event="ai.provider.status.failed",
+                message="AI provider status skipped because service URL is not configured",
+                category="ai",
+                level="warning",
+                service="ai",
+                module=__name__,
+                request_id=request_id,
+                context={**context, "status": "unconfigured"},
+            )
             return AIProviderStatusResponse(
                 provider="unconfigured",
                 enabled=False,
@@ -69,27 +91,133 @@ class AIProviderClient:
                 base_url=None,
             )
 
-        data = await self._request("GET", "/v1/provider/status", request_id=request_id)
-        return AIProviderStatusResponse.model_validate(data)
+        started_at = perf_counter()
+        await emit_business_log(
+            logger,
+            event="ai.provider.status.start",
+            message="AI provider status request started",
+            category="ai",
+            service="ai",
+            module=__name__,
+            request_id=request_id,
+            context=context,
+        )
+        try:
+            data = await self._request("GET", "/v1/provider/status", request_id=request_id, operation="status")
+            result = AIProviderStatusResponse.model_validate(data)
+            await emit_business_log(
+                logger,
+                event="ai.provider.status.success",
+                message="AI provider status request completed",
+                category="ai",
+                service="ai",
+                module=__name__,
+                request_id=request_id,
+                context={
+                    **context,
+                    "status": "success",
+                    "duration_ms": self._duration_ms(started_at),
+                    "result_provider": result.provider,
+                    "result_model": result.model,
+                    "configured": result.configured,
+                    "enabled": result.enabled,
+                },
+            )
+            return result
+        except Exception as exc:
+            await emit_business_log(
+                logger,
+                event="ai.provider.status.failed",
+                message="AI provider status request failed",
+                category="ai",
+                level="error",
+                service="ai",
+                module=__name__,
+                request_id=request_id,
+                context=exception_context(exc, {**context, "status": "failed", "duration_ms": self._duration_ms(started_at)}),
+            )
+            raise
 
     async def analyze(
         self,
         payload: SituationalAnalysisRequest,
         request_id: str | None = None,
     ) -> SituationalAnalysisResponse:
+        context = self._base_log_context(
+            operation="analyze",
+            preferred_model=payload.preferred_model,
+            input_summary=self._summarize_analysis_payload(payload),
+        )
         if not self.service_url:
+            await emit_business_log(
+                logger,
+                event="ai.provider.analyze.failed",
+                message="AI provider analyze skipped because service URL is not configured",
+                category="ai",
+                level="warning",
+                service="ai",
+                module=__name__,
+                request_id=request_id,
+                context={**context, "status": "unconfigured"},
+            )
             raise HTTPException(
                 status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
                 detail="AI provider service URL is not configured.",
             )
 
-        data = await self._request(
-            "POST",
-            "/v1/analyze",
-            json=payload.model_dump(),
+        started_at = perf_counter()
+        await emit_business_log(
+            logger,
+            event="ai.provider.analyze.start",
+            message="AI provider analyze request started",
+            category="ai",
+            service="ai",
+            module=__name__,
             request_id=request_id,
+            context=context,
         )
-        return SituationalAnalysisResponse.model_validate(data)
+        try:
+            data = await self._request(
+                "POST",
+                "/v1/analyze",
+                json=payload.model_dump(),
+                request_id=request_id,
+                operation="analyze",
+                payload_summary=context["input_summary"],
+            )
+            result = SituationalAnalysisResponse.model_validate(data)
+            await emit_business_log(
+                logger,
+                event="ai.provider.analyze.success",
+                message="AI provider analyze request completed",
+                category="ai",
+                service="ai",
+                module=__name__,
+                request_id=request_id,
+                context={
+                    **context,
+                    "status": "success",
+                    "duration_ms": self._duration_ms(started_at),
+                    "result_provider": result.provider,
+                    "result_model": result.model,
+                    "content_block_count": len(result.content_blocks or []),
+                    "thinking_block_count": len(result.thinking_blocks or []),
+                },
+            )
+            return result
+        except Exception as exc:
+            await emit_business_log(
+                logger,
+                event="ai.provider.analyze.failed",
+                message="AI provider analyze request failed",
+                category="ai",
+                level="error",
+                service="ai",
+                module=__name__,
+                request_id=request_id,
+                context=exception_context(exc, {**context, "status": "failed", "duration_ms": self._duration_ms(started_at)}),
+            )
+            raise
 
     async def _request(
         self,
@@ -97,9 +225,12 @@ class AIProviderClient:
         path: str,
         json: dict | None = None,
         request_id: str | None = None,
+        operation: str = "request",
+        payload_summary: dict | None = None,
     ) -> dict:
         last_error: Exception | None = None
         for attempt in range(1, self.retry_attempts + 1):
+            attempt_started_at = perf_counter()
             try:
                 async with httpx.AsyncClient(timeout=self.timeout) as client:
                     response = await client.request(
@@ -113,6 +244,15 @@ class AIProviderClient:
             except httpx.HTTPStatusError as exc:
                 last_error = exc
                 if attempt < self.retry_attempts and exc.response.status_code >= 500:
+                    await self._log_retry(
+                        operation=operation,
+                        request_id=request_id,
+                        attempt=attempt,
+                        status_code=exc.response.status_code,
+                        duration_ms=self._duration_ms(attempt_started_at),
+                        error=exc,
+                        payload_summary=payload_summary,
+                    )
                     await asyncio.sleep(0.3 * attempt)
                     continue
                 detail = exc.response.text or "AI provider service returned an error"
@@ -123,6 +263,14 @@ class AIProviderClient:
             except httpx.HTTPError as exc:
                 last_error = exc
                 if attempt < self.retry_attempts:
+                    await self._log_retry(
+                        operation=operation,
+                        request_id=request_id,
+                        attempt=attempt,
+                        duration_ms=self._duration_ms(attempt_started_at),
+                        error=exc,
+                        payload_summary=payload_summary,
+                    )
                     await asyncio.sleep(0.3 * attempt)
                     continue
                 raise HTTPException(
@@ -135,6 +283,71 @@ class AIProviderClient:
             detail=f"AI provider service request failed: {last_error}",
         )
 
+    def _base_log_context(self, **extra: object) -> dict:
+        llm_provider_apis = self.llm_config.get("model_provider_apis")
+        return {
+            "provider": self.llm_config.get("provider") or "",
+            "provider_api": self.llm_config.get("provider_api") or "",
+            "model": self.llm_config.get("model") or "",
+            "base_url_configured": bool(self.llm_config.get("base_url")),
+            "service_url_configured": bool(self.service_url),
+            "timeout_seconds": self.timeout,
+            "retry_attempts": self.retry_attempts,
+            "model_provider_api_count": len(llm_provider_apis or {}) if isinstance(llm_provider_apis, dict) else 0,
+            **extra,
+        }
+
+    @staticmethod
+    def _duration_ms(started_at: float) -> int:
+        return int((perf_counter() - started_at) * 1000)
+
+    @staticmethod
+    def _summarize_analysis_payload(payload: SituationalAnalysisRequest) -> dict:
+        context = payload.context if isinstance(payload.context, dict) else {}
+        thinking = payload.thinking if isinstance(payload.thinking, dict) else payload.thinking
+        return {
+            "title_length": len(payload.title or ""),
+            "objective_length": len(payload.objective or ""),
+            "observation_count": len(payload.observations or []),
+            "constraint_count": len(payload.constraints or []),
+            "has_system_prompt": bool(payload.system_prompt),
+            "thinking_enabled": bool(thinking),
+            "context_keys": sorted(str(key) for key in context.keys()),
+        }
+
+    async def _log_retry(
+        self,
+        *,
+        operation: str,
+        request_id: str | None,
+        attempt: int,
+        duration_ms: int,
+        error: BaseException,
+        status_code: int | None = None,
+        payload_summary: dict | None = None,
+    ) -> None:
+        await emit_business_log(
+            logger,
+            event=f"ai.provider.{operation}.retry",
+            message="AI provider request will retry",
+            category="ai",
+            level="warning",
+            service="ai",
+            module=__name__,
+            request_id=request_id,
+            context=exception_context(
+                error,
+                {
+                    **self._base_log_context(operation=operation),
+                    "attempt": attempt,
+                    "next_attempt": attempt + 1,
+                    "status_code": status_code,
+                    "duration_ms": duration_ms,
+                    "input_summary": payload_summary,
+                },
+            ),
+        )
+
 
 async def get_ai_provider_client(db: AsyncSession = Depends(get_db)) -> AIProviderClient:
     from app.api.v1.settings import get_runtime_ai_provider_config

backend/app/services/ai_tools/__init__.py

@@ -0,0 +1,7 @@
+"""Backend-owned AI tool services.
+
+The services in this package are business tools used by Planet's backend
+orchestrators. They intentionally live outside ``aiprovider`` so model transport
+stays separate from evidence collection and domain policy.
+"""
+

backend/app/services/ai_tools/evidence_store.py

@@ -0,0 +1,48 @@
+from __future__ import annotations
+
+import hashlib
+from typing import Iterable
+
+from app.services.ai_tools.schemas import FetchedEvidence, SearchEvidence
+
+
+def evidence_content_hash(text: str) -> str:
+    return hashlib.sha256(text.encode("utf-8")).hexdigest()
+
+
+def normalize_search_evidence(items: Iterable[SearchEvidence], *, limit: int = 5) -> list[dict]:
+    normalized: list[dict] = []
+    seen_urls: set[str] = set()
+    for item in items:
+        if not item.url or item.url in seen_urls:
+            continue
+        seen_urls.add(item.url)
+        normalized.append(
+            {
+                "title": item.title,
+                "url": item.url,
+                "snippet": item.snippet,
+                "content": item.compact_text(),
+                "score": item.score,
+                "source_provider": item.source_provider,
+                "retrieved_at": item.retrieved_at.isoformat(),
+                "metadata": item.metadata,
+            }
+        )
+        if len(normalized) >= limit:
+            break
+    return normalized
+
+
+def normalize_fetched_evidence(item: FetchedEvidence, *, text_limit: int = 1200) -> dict:
+    text = " ".join(item.text.split())[:text_limit]
+    return {
+        "title": item.title,
+        "url": item.final_url or item.url,
+        "text": text,
+        "content_hash": item.content_hash or evidence_content_hash(item.text),
+        "extractor": item.extractor,
+        "retrieved_at": item.retrieved_at.isoformat(),
+        "metadata": item.metadata,
+    }
+

backend/app/services/ai_tools/schemas.py

@@ -0,0 +1,63 @@
+from __future__ import annotations
+
+from datetime import UTC, datetime
+from typing import Any
+
+from pydantic import BaseModel, Field
+
+
+class SearchEvidence(BaseModel):
+    title: str = ""
+    url: str = ""
+    snippet: str = ""
+    content: str = ""
+    score: float | None = None
+    source_provider: str = ""
+    retrieved_at: datetime = Field(default_factory=lambda: datetime.now(UTC))
+    metadata: dict[str, Any] = Field(default_factory=dict)
+
+    def compact_text(self, limit: int = 700) -> str:
+        text = " ".join((self.content or self.snippet or "").split())
+        return text[:limit]
+
+
+class FetchedEvidence(BaseModel):
+    url: str
+    final_url: str = ""
+    title: str = ""
+    text: str = ""
+    content_hash: str = ""
+    extractor: str = "basic_html"
+    retrieved_at: datetime = Field(default_factory=lambda: datetime.now(UTC))
+    metadata: dict[str, Any] = Field(default_factory=dict)
+
+
+class WebSearchProviderConfig(BaseModel):
+    provider: str = "tavily"
+    base_url: str = ""
+    api_key: str = ""
+    max_results: int = Field(default=5, ge=1, le=20)
+    timeout_seconds: int = Field(default=20, ge=3, le=120)
+    endpoint_path: str = ""
+    search_depth: str = "basic"
+    engine: str = "google"
+    include_answer: bool = False
+    include_raw_content: bool = False
+    include_text: bool = False
+    categories: str = "general"
+    engines: list[str] = Field(default_factory=list)
+    search_path: str = ""
+    scrape_path: str = ""
+    scrape_formats: list[str] = Field(default_factory=lambda: ["markdown"])
+
+
+class WebSearchConfig(BaseModel):
+    enabled: bool = False
+    default_provider: str = "tavily"
+    provider: str = "tavily"
+    providers: dict[str, WebSearchProviderConfig] = Field(default_factory=dict)
+
+    @property
+    def active_provider_config(self) -> WebSearchProviderConfig:
+        return self.providers.get(self.default_provider) or self.providers.get(self.provider) or WebSearchProviderConfig(provider=self.default_provider or self.provider)
+

backend/app/services/ai_tools/web_fetch.py

@@ -0,0 +1,122 @@
+from __future__ import annotations
+
+import hashlib
+from time import perf_counter
+from urllib.parse import urlparse
+
+import httpx
+from bs4 import BeautifulSoup
+
+from app.core.logging import get_logger
+from app.services.ai_tools.schemas import FetchedEvidence
+from app.services.business_logs import emit_business_log, exception_context
+
+
+logger = get_logger(__name__, service="ai_tool")
+
+
+class WebFetchError(RuntimeError):
+    pass
+
+
+def _extract_title_and_text(html: str) -> tuple[str, str]:
+    soup = BeautifulSoup(html, "html.parser")
+    for tag in soup(["script", "style", "noscript", "svg"]):
+        tag.decompose()
+    title = soup.title.get_text(" ", strip=True) if soup.title else ""
+    main = soup.find("main") or soup.find("article") or soup.body or soup
+    text = main.get_text("\n", strip=True)
+    lines = [line.strip() for line in text.splitlines() if line.strip()]
+    return title, "\n".join(lines)
+
+
+async def fetch_url_evidence(
+    url: str,
+    *,
+    timeout_seconds: int = 20,
+    max_bytes: int = 1_500_000,
+) -> FetchedEvidence:
+    started_at = perf_counter()
+    if not url:
+        await emit_business_log(
+            logger,
+            event="ai_tool.web_fetch.failed",
+            message="WebFetch failed because URL is empty",
+            category="ai_tool",
+            level="warning",
+            service="ai_tool",
+            module=__name__,
+            context={"reason": "empty_url"},
+        )
+        raise WebFetchError("url is required")
+    request_host = urlparse(url).netloc
+    await emit_business_log(
+        logger,
+        event="ai_tool.web_fetch.start",
+        message="WebFetch request started",
+        category="ai_tool",
+        service="ai_tool",
+        module=__name__,
+        context={
+            "url_host": request_host,
+            "timeout_seconds": timeout_seconds,
+            "max_bytes": max_bytes,
+        },
+    )
+    try:
+        async with httpx.AsyncClient(
+            timeout=timeout_seconds,
+            follow_redirects=True,
+            headers={"User-Agent": "PlanetEvidenceFetcher/1.0"},
+        ) as client:
+            response = await client.get(url)
+            response.raise_for_status()
+            content = response.content[:max_bytes]
+    except httpx.HTTPError as exc:
+        await emit_business_log(
+            logger,
+            event="ai_tool.web_fetch.failed",
+            message="WebFetch request failed",
+            category="ai_tool",
+            level="error",
+            service="ai_tool",
+            module=__name__,
+            context=exception_context(
+                exc,
+                {
+                    "url_host": request_host,
+                    "status": "failed",
+                    "duration_ms": int((perf_counter() - started_at) * 1000),
+                },
+            ),
+        )
+        raise WebFetchError(f"failed to fetch page: {exc}") from exc
+
+    title, text = _extract_title_and_text(content.decode(response.encoding or "utf-8", errors="ignore"))
+    content_hash = hashlib.sha256(text.encode("utf-8")).hexdigest()
+    await emit_business_log(
+        logger,
+        event="ai_tool.web_fetch.success",
+        message="WebFetch request completed",
+        category="ai_tool",
+        service="ai_tool",
+        module=__name__,
+        context={
+            "url_host": request_host,
+            "final_url_host": urlparse(str(response.url)).netloc,
+            "status": "success",
+            "status_code": response.status_code,
+            "bytes_read": len(content),
+            "content_hash": content_hash,
+            "duration_ms": int((perf_counter() - started_at) * 1000),
+            "extractor": "beautifulsoup_basic",
+        },
+    )
+    return FetchedEvidence(
+        url=url,
+        final_url=str(response.url),
+        title=title,
+        text=text,
+        content_hash=content_hash,
+        extractor="beautifulsoup_basic",
+    )

backend/app/services/ai_tools/web_search.py

@@ -0,0 +1,476 @@
+from __future__ import annotations
+
+from copy import deepcopy
+import hashlib
+from time import perf_counter
+from typing import Any
+
+import httpx
+
+from app.core.logging import get_logger
+from app.services.ai_tools.schemas import SearchEvidence, WebSearchConfig, WebSearchProviderConfig
+from app.services.business_logs import emit_business_log, exception_context
+
+
+logger = get_logger(__name__, service="ai_tool")
+
+
+WEB_SEARCH_PROVIDER_PRESETS: dict[str, dict[str, Any]] = {
+    "tavily": {
+        "provider": "tavily",
+        "label": "Tavily",
+        "api_key_env": "TAVILY_API_KEY",
+        "base_url": "https://api.tavily.com",
+        "endpoint_path": "/search",
+        "max_results": 5,
+        "timeout_seconds": 20,
+        "search_depth": "basic",
+        "include_answer": False,
+        "include_raw_content": False,
+    },
+    "brave": {
+        "provider": "brave",
+        "label": "Brave Search API",
+        "api_key_env": "BRAVE_SEARCH_API_KEY",
+        "base_url": "https://api.search.brave.com",
+        "endpoint_path": "/res/v1/web/search",
+        "max_results": 5,
+        "timeout_seconds": 20,
+    },
+    "serpapi": {
+        "provider": "serpapi",
+        "label": "SerpAPI",
+        "api_key_env": "SERPAPI_API_KEY",
+        "base_url": "https://serpapi.com",
+        "endpoint_path": "/search.json",
+        "engine": "google",
+        "max_results": 5,
+        "timeout_seconds": 20,
+    },
+    "exa": {
+        "provider": "exa",
+        "label": "Exa",
+        "api_key_env": "EXA_API_KEY",
+        "base_url": "https://api.exa.ai",
+        "endpoint_path": "/search",
+        "max_results": 5,
+        "timeout_seconds": 20,
+        "include_text": False,
+    },
+    "firecrawl": {
+        "provider": "firecrawl",
+        "label": "Firecrawl Search / Scrape",
+        "api_key_env": "FIRECRAWL_API_KEY",
+        "base_url": "https://api.firecrawl.dev",
+        "search_path": "/v2/search",
+        "scrape_path": "/v2/scrape",
+        "max_results": 5,
+        "timeout_seconds": 30,
+        "scrape_formats": ["markdown"],
+    },
+    "searxng": {
+        "provider": "searxng",
+        "label": "SearXNG",
+        "api_key_env": "SEARXNG_API_KEY",
+        "base_url": "http://localhost:8080",
+        "endpoint_path": "/",
+        "max_results": 5,
+        "timeout_seconds": 20,
+        "categories": "general",
+        "engines": [],
+    },
+}
+
+
+class WebSearchError(RuntimeError):
+    pass
+
+
+class WebSearchConfigurationError(WebSearchError):
+    pass
+
+
+def normalize_web_search_provider(provider: str | None) -> str:
+    return (provider or "tavily").strip().lower() or "tavily"
+
+
+def get_web_search_provider_preset(provider: str) -> dict[str, Any]:
+    provider_id = normalize_web_search_provider(provider)
+    preset = WEB_SEARCH_PROVIDER_PRESETS.get(provider_id)
+    if not preset:
+        raise ValueError(f"Unsupported web search provider: {provider}")
+    return deepcopy(preset)
+
+
+def list_web_search_provider_presets() -> list[dict[str, Any]]:
+    return [get_web_search_provider_preset(provider) for provider in WEB_SEARCH_PROVIDER_PRESETS]
+
+
+def provider_defaults(provider: str) -> WebSearchProviderConfig:
+    preset = get_web_search_provider_preset(provider)
+    return WebSearchProviderConfig(**{
+        key: value
+        for key, value in preset.items()
+        if key in WebSearchProviderConfig.model_fields
+    })
+
+
+class WebSearchClient:
+    def __init__(self, config: WebSearchConfig) -> None:
+        self.config = config
+
+    async def search(
+        self,
+        query: str,
+        *,
+        max_results: int | None = None,
+        domains: list[str] | None = None,
+        freshness_days: int | None = None,
+    ) -> list[SearchEvidence]:
+        started_at = perf_counter()
+        if not self.config.enabled:
+            await emit_business_log(
+                logger,
+                event="ai_tool.web_search.unavailable",
+                message="WebSearch skipped because integration is disabled",
+                category="ai_tool",
+                level="warning",
+                service="ai_tool",
+                module=__name__,
+                context={"provider": self.config.default_provider, "reason": "disabled"},
+            )
+            raise WebSearchConfigurationError("WebSearch is disabled.")
+        provider_config = self.config.active_provider_config
+        provider = normalize_web_search_provider(provider_config.provider)
+        if provider != "searxng" and not provider_config.api_key:
+            await emit_business_log(
+                logger,
+                event="ai_tool.web_search.unavailable",
+                message="WebSearch skipped because API key is not configured",
+                category="ai_tool",
+                level="warning",
+                service="ai_tool",
+                module=__name__,
+                context={"provider": provider, "reason": "missing_api_key"},
+            )
+            raise WebSearchConfigurationError(f"{provider} API key is not configured.")
+        query = " ".join(str(query or "").split())
+        if not query:
+            await emit_business_log(
+                logger,
+                event="ai_tool.web_search.failed",
+                message="WebSearch failed because query is empty",
+                category="ai_tool",
+                level="warning",
+                service="ai_tool",
+                module=__name__,
+                context={"provider": provider, "reason": "empty_query"},
+            )
+            raise WebSearchConfigurationError("search query is required.")
+        limit = max_results or provider_config.max_results
+        context = {
+            "provider": provider,
+            "query_hash": hashlib.sha256(query.encode("utf-8")).hexdigest(),
+            "query_length": len(query),
+            "max_results": limit,
+            "domain_count": len(domains or []),
+            "freshness_days": freshness_days,
+        }
+        await emit_business_log(
+            logger,
+            event="ai_tool.web_search.start",
+            message="WebSearch request started",
+            category="ai_tool",
+            service="ai_tool",
+            module=__name__,
+            context=context,
+        )
+        try:
+            if provider == "tavily":
+                results = await self._search_tavily(provider_config, query, limit, domains, freshness_days)
+            elif provider == "brave":
+                results = await self._search_brave(provider_config, query, limit, domains)
+            elif provider == "serpapi":
+                results = await self._search_serpapi(provider_config, query, limit)
+            elif provider == "exa":
+                results = await self._search_exa(provider_config, query, limit, domains)
+            elif provider == "firecrawl":
+                results = await self._search_firecrawl(provider_config, query, limit)
+            elif provider == "searxng":
+                results = await self._search_searxng(provider_config, query, limit, domains)
+            else:
+                raise WebSearchConfigurationError(f"Unsupported web search provider: {provider}")
+            event = "ai_tool.web_search.success" if results else "ai_tool.web_search.empty"
+            await emit_business_log(
+                logger,
+                event=event,
+                message="WebSearch request completed" if results else "WebSearch returned no results",
+                category="ai_tool",
+                level="info" if results else "warning",
+                service="ai_tool",
+                module=__name__,
+                context={
+                    **context,
+                    "status": "success" if results else "empty",
+                    "result_count": len(results),
+                    "duration_ms": int((perf_counter() - started_at) * 1000),
+                },
+            )
+            return results
+        except Exception as exc:
+            await emit_business_log(
+                logger,
+                event="ai_tool.web_search.failed",
+                message="WebSearch request failed",
+                category="ai_tool",
+                level="error",
+                service="ai_tool",
+                module=__name__,
+                context=exception_context(exc, {**context, "status": "failed", "duration_ms": int((perf_counter() - started_at) * 1000)}),
+            )
+            raise
+
+    async def test_connection(self) -> list[SearchEvidence]:
+        return await self.search("Planet WebSearch connectivity test", max_results=1)
+
+    async def _request_json(
+        self,
+        method: str,
+        url: str,
+        *,
+        provider_config: WebSearchProviderConfig,
+        headers: dict[str, str] | None = None,
+        params: dict[str, Any] | None = None,
+        json: dict[str, Any] | None = None,
+    ) -> dict[str, Any]:
+        try:
+            async with httpx.AsyncClient(timeout=provider_config.timeout_seconds) as client:
+                response = await client.request(
+                    method,
+                    url,
+                    headers=headers,
+                    params=params,
+                    json=json,
+                )
+                response.raise_for_status()
+                data = response.json()
+        except httpx.HTTPStatusError as exc:
+            detail = exc.response.text or exc.response.reason_phrase
+            raise WebSearchError(f"{provider_config.provider} request failed: {detail}") from exc
+        except httpx.HTTPError as exc:
+            raise WebSearchError(f"{provider_config.provider} request failed: {exc}") from exc
+        except ValueError as exc:
+            raise WebSearchError(f"{provider_config.provider} returned invalid JSON") from exc
+        return data if isinstance(data, dict) else {}
+
+    async def _search_tavily(
+        self,
+        config: WebSearchProviderConfig,
+        query: str,
+        max_results: int,
+        domains: list[str] | None,
+        freshness_days: int | None,
+    ) -> list[SearchEvidence]:
+        body: dict[str, Any] = {
+            "api_key": config.api_key,
+            "query": query,
+            "max_results": max_results,
+            "search_depth": config.search_depth or "basic",
+            "include_answer": config.include_answer,
+            "include_raw_content": config.include_raw_content,
+        }
+        if domains:
+            body["include_domains"] = domains
+        if freshness_days:
+            body["days"] = freshness_days
+        data = await self._request_json(
+            "POST",
+            _join_url(config.base_url, config.endpoint_path or "/search"),
+            provider_config=config,
+            json=body,
+        )
+        return [
+            SearchEvidence(
+                title=str(item.get("title") or ""),
+                url=str(item.get("url") or ""),
+                snippet=str(item.get("content") or ""),
+                content=str(item.get("raw_content") or ""),
+                score=_float_or_none(item.get("score")),
+                source_provider="tavily",
+                metadata={"query": data.get("query") or query},
+            )
+            for item in data.get("results") or []
+            if isinstance(item, dict) and item.get("url")
+        ]
+
+    async def _search_brave(
+        self,
+        config: WebSearchProviderConfig,
+        query: str,
+        max_results: int,
+        domains: list[str] | None,
+    ) -> list[SearchEvidence]:
+        search_query = query
+        if domains:
+            search_query = f"{query} " + " ".join(f"site:{domain}" for domain in domains)
+        data = await self._request_json(
+            "GET",
+            _join_url(config.base_url, config.endpoint_path or "/res/v1/web/search"),
+            provider_config=config,
+            headers={"X-Subscription-Token": config.api_key},
+            params={"q": search_query, "count": max_results},
+        )
+        results = (data.get("web") or {}).get("results") or []
+        return [
+            SearchEvidence(
+                title=str(item.get("title") or ""),
+                url=str(item.get("url") or ""),
+                snippet=str(item.get("description") or ""),
+                source_provider="brave",
+                metadata={"age": item.get("age")},
+            )
+            for item in results
+            if isinstance(item, dict) and item.get("url")
+        ]
+
+    async def _search_serpapi(
+        self,
+        config: WebSearchProviderConfig,
+        query: str,
+        max_results: int,
+    ) -> list[SearchEvidence]:
+        data = await self._request_json(
+            "GET",
+            _join_url(config.base_url, config.endpoint_path or "/search.json"),
+            provider_config=config,
+            params={
+                "api_key": config.api_key,
+                "engine": config.engine or "google",
+                "q": query,
+                "num": max_results,
+            },
+        )
+        return [
+            SearchEvidence(
+                title=str(item.get("title") or ""),
+                url=str(item.get("link") or ""),
+                snippet=str(item.get("snippet") or ""),
+                source_provider="serpapi",
+                metadata={"position": item.get("position")},
+            )
+            for item in data.get("organic_results") or []
+            if isinstance(item, dict) and item.get("link")
+        ]
+
+    async def _search_exa(
+        self,
+        config: WebSearchProviderConfig,
+        query: str,
+        max_results: int,
+        domains: list[str] | None,
+    ) -> list[SearchEvidence]:
+        body: dict[str, Any] = {
+            "query": query,
+            "numResults": max_results,
+        }
+        if domains:
+            body["includeDomains"] = domains
+        if config.include_text:
+            body["contents"] = {"text": True}
+        data = await self._request_json(
+            "POST",
+            _join_url(config.base_url, config.endpoint_path or "/search"),
+            provider_config=config,
+            headers={"Authorization": f"Bearer {config.api_key}"},
+            json=body,
+        )
+        return [
+            SearchEvidence(
+                title=str(item.get("title") or ""),
+                url=str(item.get("url") or ""),
+                snippet=str(item.get("summary") or ""),
+                content=str(item.get("text") or ""),
+                score=_float_or_none(item.get("score")),
+                source_provider="exa",
+                metadata={"id": item.get("id")},
+            )
+            for item in data.get("results") or []
+            if isinstance(item, dict) and item.get("url")
+        ]
+
+    async def _search_firecrawl(
+        self,
+        config: WebSearchProviderConfig,
+        query: str,
+        max_results: int,
+    ) -> list[SearchEvidence]:
+        data = await self._request_json(
+            "POST",
+            _join_url(config.base_url, config.search_path or "/v2/search"),
+            provider_config=config,
+            headers={"Authorization": f"Bearer {config.api_key}"},
+            json={"query": query, "limit": max_results},
+        )
+        raw_results = data.get("data") or data.get("results") or []
+        return [
+            SearchEvidence(
+                title=str(item.get("title") or ""),
+                url=str(item.get("url") or item.get("sourceURL") or ""),
+                snippet=str(item.get("description") or item.get("markdown") or ""),
+                source_provider="firecrawl",
+                metadata={"status": item.get("status")},
+            )
+            for item in raw_results
+            if isinstance(item, dict) and (item.get("url") or item.get("sourceURL"))
+        ]
+
+    async def _search_searxng(
+        self,
+        config: WebSearchProviderConfig,
+        query: str,
+        max_results: int,
+        domains: list[str] | None,
+    ) -> list[SearchEvidence]:
+        search_query = query
+        if domains:
+            search_query = f"{query} " + " ".join(f"site:{domain}" for domain in domains)
+        params: dict[str, Any] = {
+            "q": search_query,
+            "format": "json",
+            "categories": config.categories or "general",
+        }
+        if config.engines:
+            params["engines"] = ",".join(config.engines)
+        headers = {"Authorization": f"Bearer {config.api_key}"} if config.api_key else None
+        data = await self._request_json(
+            "GET",
+            _join_url(config.base_url, config.endpoint_path or "/"),
+            provider_config=config,
+            headers=headers,
+            params=params,
+        )
+        results = data.get("results") or []
+        evidence = [
+            SearchEvidence(
+                title=str(item.get("title") or ""),
+                url=str(item.get("url") or ""),
+                snippet=str(item.get("content") or ""),
+                score=_float_or_none(item.get("score")),
+                source_provider="searxng",
+                metadata={"engine": item.get("engine")},
+            )
+            for item in results
+            if isinstance(item, dict) and item.get("url")
+        ]
+        return evidence[:max_results]
+
+
+def _join_url(base_url: str, path: str) -> str:
+    return f"{(base_url or '').rstrip('/')}/{(path or '').lstrip('/')}"
+
+
+def _float_or_none(value: Any) -> float | None:
+    try:
+        return float(value)
+    except (TypeError, ValueError):
+        return None

backend/app/services/alert_ai_brief.py

@@ -8,6 +8,9 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.models.alert import Alert, AlertSeverity, AlertStatus
 from app.schemas.ai import AlertBriefRequest, SituationalAnalysisRequest
+from app.ai_tasks.prompts import get_effective_prompt
+
+ALERT_BRIEF_PROMPT_KEY = "alerts.brief"
 
 
 def _format_counter(counter: Counter[str], empty_text: str = "无") -> str:
@@ -84,11 +87,13 @@ async def build_alert_brief_request(
         "top_datasources": dict(datasource_counts.most_common(6)),
         "top_active_datasources": dict(active_datasource_counts.most_common(5)),
     }
+    prompt = await get_effective_prompt(db, ALERT_BRIEF_PROMPT_KEY)
 
     return (
         SituationalAnalysisRequest(
             title="告警态势 AI 简报",
-            objective="基于当前告警总量、严重度、状态、数据源分布与最近告警摘录，生成一份面向值班人员的简明告警态势简报，突出待处理风险、告警集中点和优先动作。",
+            objective=prompt.prompt,
+            system_prompt=prompt.system_prompt or None,
             observations=facts,
             constraints=[
                 "明确区分事实、推断与建议。",

backend/app/services/bgp_ai_brief.py

@@ -11,9 +11,12 @@ from app.models.bgp_anomaly import BGPAnomaly
 from app.models.bgp_incident import BGPIncident
 from app.models.bgp_observation import BGPObservation
 from app.schemas.ai import SituationalAnalysisRequest
+from app.ai_tasks.prompts import get_effective_prompt
 from app.services.bgp_collectors import build_bgp_collector_coverage
 from app.services.bgp_enrichment import lookup_prefix_geography
 
+BGP_BRIEF_PROMPT_KEY = "bgp.brief"
+
 
 def _format_counter(counter: dict[str, int], empty_text: str = "无") -> str:
     if not counter:
@@ -243,12 +246,15 @@ async def build_bgp_brief_request(
             for prefix, item in list(prefix_geographies.items())[:8]
         },
     }
+    prompt = await get_effective_prompt(db, BGP_BRIEF_PROMPT_KEY)
 
     return SituationalAnalysisRequest(
         title="BGP 态势 AI 简报",
-        objective="基于当前 BGP incidents、anomalies、原始观测事件、观测站覆盖与 prefix geography 证据，生成一份面向操作员的简明态势简报，突出区域热点、观测偏差、当前风险、证据和优先动作。",
+        objective=prompt.prompt,
+        system_prompt=prompt.system_prompt or None,
         observations=observations_lines,
         constraints=[
+            "直接输出中文 Markdown 简报正文，不要输出英文写作计划、提示词复述、字段说明或元评论。",
             "明确区分事实、推断与建议。",
             "优先指出需要立即关注的高严重度 incident 或异常模式。",
             "需要单独指出哪些区域结论来自 prefix geography / affected regions，哪些可能受 collector coverage 偏差影响。",

backend/app/services/bgp_collector_locations.py

@@ -291,9 +291,27 @@ def collect_bgp_collector_location_candidates(
     site: str | None = None,
     operator: str | None = None,
 ) -> tuple[list[LocationCandidate], list[str]]:
+    query = build_bgp_collector_location_query(
+        collector=collector,
+        city=city,
+        country=country,
+        site=site,
+        operator=operator,
+    )
+    return BGP_COLLECTOR_COLLECTION_PIPELINE.collect_candidates(query)
+
+
+def build_bgp_collector_location_query(
+    *,
+    collector: str | None = None,
+    city: str | None = None,
+    country: str | None = None,
+    site: str | None = None,
+    operator: str | None = None,
+) -> LocationQuery:
     stored = get_bgp_collector_location_dict(collector or "")
     name = coerce_str(collector) or None
-    query = LocationQuery(
+    return LocationQuery(
         name=name,
         aliases=tuple(filter(None, (collector,))),
         city=coerce_str(city or stored.get("city")) or None,
@@ -301,6 +319,6 @@ def collect_bgp_collector_location_candidates(
         extra={
             "site": coerce_str(site or stored.get("site")),
             "operator": coerce_str(operator or stored.get("operator")) or "RIPE NCC",
+            "collector": coerce_str(collector),
         },
     )
-    return BGP_COLLECTOR_COLLECTION_PIPELINE.collect_candidates(query)

backend/app/services/business_logs.py

@@ -0,0 +1,117 @@
+from __future__ import annotations
+
+import asyncio
+from collections.abc import Mapping
+from typing import Any
+
+from app.core.logging import PlanetLoggerAdapter, sanitize_log_value
+from app.core.request_context import get_request_id
+from app.services.persistent_logs import record_system_log
+
+
+LEVEL_METHODS = {
+    "debug": "debug_event",
+    "info": "info_event",
+    "warning": "warning_event",
+    "error": "error_event",
+}
+
+
+def normalize_business_level(level: str | None) -> str:
+    normalized = str(level or "info").strip().lower()
+    if normalized in {"warn", "warning"}:
+        return "warning"
+    if normalized in {"err", "error", "critical", "fatal"}:
+        return "error"
+    if normalized == "debug":
+        return "debug"
+    return "info"
+
+
+def build_business_context(
+    context: Mapping[str, Any] | None = None,
+    **fields: Any,
+) -> dict[str, Any]:
+    payload = dict(context or {})
+    for key, value in fields.items():
+        if value is not None:
+            payload[key] = value
+    return sanitize_log_value(payload)
+
+
+async def emit_business_log(
+    logger: PlanetLoggerAdapter,
+    *,
+    event: str,
+    message: str,
+    category: str,
+    level: str = "info",
+    source: str = "backend",
+    service: str | None = None,
+    module: str | None = None,
+    request_id: str | None = None,
+    user_id: int | None = None,
+    context: Mapping[str, Any] | None = None,
+) -> None:
+    normalized_level = normalize_business_level(level)
+    safe_context = build_business_context(context)
+    log_method = getattr(logger, LEVEL_METHODS[normalized_level])
+    log_method(message, event=event, context=safe_context)
+    await record_system_log(
+        source=source,
+        level=normalized_level,
+        message=message,
+        service=service,
+        module=module,
+        event=event,
+        request_id=request_id or get_request_id(),
+        user_id=user_id,
+        category=category,
+        context=safe_context,
+    )
+
+
+def emit_business_log_background(
+    logger: PlanetLoggerAdapter,
+    *,
+    event: str,
+    message: str,
+    category: str,
+    level: str = "info",
+    source: str = "backend",
+    service: str | None = None,
+    module: str | None = None,
+    request_id: str | None = None,
+    user_id: int | None = None,
+    context: Mapping[str, Any] | None = None,
+) -> None:
+    normalized_level = normalize_business_level(level)
+    safe_context = build_business_context(context)
+    log_method = getattr(logger, LEVEL_METHODS[normalized_level])
+    log_method(message, event=event, context=safe_context)
+    try:
+        loop = asyncio.get_running_loop()
+    except RuntimeError:
+        return
+    loop.create_task(
+        record_system_log(
+            source=source,
+            level=normalized_level,
+            message=message,
+            service=service,
+            module=module,
+            event=event,
+            request_id=request_id or get_request_id(),
+            user_id=user_id,
+            category=category,
+            context=safe_context,
+        )
+    )
+
+
+def exception_context(exc: BaseException, context: Mapping[str, Any] | None = None) -> dict[str, Any]:
+    return build_business_context(
+        context,
+        error_type=type(exc).__name__,
+        error=str(exc),
+    )

backend/app/services/collectors/__init__.py

@@ -36,6 +36,7 @@ from app.services.collectors.iptoasn import IPtoASNPrefixGeoCollector
 from app.services.collectors.opengeofeed import OpenGeoFeedPrefixGeoCollector
 from app.services.collectors.nro_delegated import NRODelegatedPrefixGeoCollector
 from app.services.collectors.news_live_streams import NewsLiveStreamsCollector
+from app.services.collectors.media_news_archive import MediaNewsArchiveCollector
 from app.services.collectors.aisstream import AISStreamCollector
 from app.services.collectors.vessel_ais import VesselAISCollector
 
@@ -65,6 +66,7 @@ collector_registry.register(IPtoASNPrefixGeoCollector())
 collector_registry.register(OpenGeoFeedPrefixGeoCollector())
 collector_registry.register(NRODelegatedPrefixGeoCollector())
 collector_registry.register(NewsLiveStreamsCollector())
+collector_registry.register(MediaNewsArchiveCollector())
 collector_registry.register(VesselAISCollector())
 collector_registry.register(AISStreamCollector())
 
@@ -100,6 +102,7 @@ __all__ = [
     "OpenGeoFeedPrefixGeoCollector",
     "NRODelegatedPrefixGeoCollector",
     "NewsLiveStreamsCollector",
+    "MediaNewsArchiveCollector",
     "VesselAISCollector",
     "AISStreamCollector",
 ]

backend/app/services/collectors/aisstream.py

@@ -138,7 +138,7 @@ class AISStreamCollector(BaseCollector):
 
         try:
             import websockets
-        except ImportError as exc:
+        except ImportError:
             return {"status": "failed", "error": "Python package 'websockets' is required for AISStream"}
 
         start_time = datetime.now(UTC)

backend/app/services/collectors/base.py

@@ -4,15 +4,22 @@ import asyncio
 from abc import ABC, abstractmethod
 from typing import Dict, List, Any, Optional
 from datetime import UTC, datetime
+from time import perf_counter
+from urllib.parse import urlparse
 import httpx
 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.logging import get_logger
 from app.core.time import to_iso8601_utc
 from app.core.websocket.broadcaster import broadcaster
+from app.services.business_logs import emit_business_log, exception_context
+from app.services.earth_layer_adapters import get_earth_update_layers_for_source
+
+
+logger = get_logger(__name__, service="collector")
 
 
 class BaseCollector(ABC):
@@ -31,6 +38,7 @@ class BaseCollector(ABC):
         self._datasource_id = 1
         self._resolved_url: Optional[str] = None
         self._last_broadcast_progress: Optional[int] = None
+        self._last_save_summary: dict[str, int] = {}
 
     async def resolve_url(self, db: AsyncSession) -> None:
         from app.core.data_sources import get_data_sources_config
@@ -186,7 +194,7 @@ class BaseCollector(ABC):
 
         result = await db.execute(
             select(DataSnapshot)
-            .where(DataSnapshot.source == self.name, DataSnapshot.is_current == True)
+            .where(DataSnapshot.source == self.name, DataSnapshot.is_current.is_(True))
             .order_by(DataSnapshot.completed_at.desc().nullslast(), DataSnapshot.id.desc())
             .limit(1)
         )
@@ -272,19 +280,39 @@ class BaseCollector(ABC):
         from app.models.data_snapshot import DataSnapshot
 
         start_time = datetime.now(UTC)
+        started_at = perf_counter()
         datasource_id = getattr(self, "_datasource_id", 1)
         snapshot_id: Optional[int] = None
 
         if not collector_registry.is_active(self.name):
+            await self._log_collection_event(
+                "collector.run.skipped_disabled",
+                "Collector skipped because it is disabled",
+                level="info",
+                context={"status": "skipped", "reason": "disabled"},
+            )
             return {"status": "skipped", "reason": "Collector is disabled"}
 
-        task = CollectionTask(
-            datasource_id=datasource_id,
-            status="running",
-            phase="queued",
-            started_at=start_time,
-        )
-        db.add(task)
+        task = self._current_task if isinstance(self._current_task, CollectionTask) else None
+        if task is None:
+            task = CollectionTask(
+                datasource_id=datasource_id,
+                source=self.name,
+                task_type="collect",
+                status="running",
+                phase="queued",
+                started_at=start_time,
+            )
+            db.add(task)
+        else:
+            task.datasource_id = datasource_id
+            task.source = task.source or self.name
+            task.task_type = task.task_type or "collect"
+            task.status = "running"
+            task.phase = "queued"
+            task.started_at = task.started_at or start_time
+            task.completed_at = None
+            task.error_message = None
         await db.commit()
         task_id = task.id
 
@@ -294,23 +322,76 @@ class BaseCollector(ABC):
 
         await self.resolve_url(db)
         await self._publish_task_update(force=True)
+        await self._log_collection_event(
+            "collector.run.started",
+            "Collector run started",
+            context={"status": "running", "task_id": task_id},
+        )
 
         try:
+            phase_started_at = perf_counter()
             await self.set_phase("fetching", message="正在拉取原始数据")
+            await self._log_collection_event(
+                "collector.phase.fetching.start",
+                "Collector fetch phase started",
+                context={"task_id": task_id, "snapshot_id": snapshot_id},
+            )
             raw_data = await self.fetch()
             task.total_records = len(raw_data)
             await db.commit()
             await self._publish_task_update(force=True)
+            await self._log_collection_event(
+                "collector.phase.fetching.success",
+                "Collector fetch phase completed",
+                context={
+                    "task_id": task_id,
+                    "raw_count": len(raw_data),
+                    "duration_ms": self._duration_ms(phase_started_at),
+                },
+            )
 
             if self.fail_on_empty and not raw_data:
                 raise RuntimeError(f"Collector {self.name} returned no data")
 
+            phase_started_at = perf_counter()
             await self.set_phase("transforming", message="正在转换采集数据")
+            await self._log_collection_event(
+                "collector.phase.transforming.start",
+                "Collector transform phase started",
+                context={"task_id": task_id, "raw_count": len(raw_data)},
+            )
             data = self.transform(raw_data)
+            await self._log_collection_event(
+                "collector.phase.transforming.success",
+                "Collector transform phase completed",
+                context={
+                    "task_id": task_id,
+                    "raw_count": len(raw_data),
+                    "transformed_count": len(data),
+                    "duration_ms": self._duration_ms(phase_started_at),
+                },
+            )
             snapshot_id = await self._create_snapshot(db, task_id, data, start_time)
 
+            phase_started_at = perf_counter()
             await self.set_phase("saving", message="正在保存采集数据")
+            await self._log_collection_event(
+                "collector.phase.saving.start",
+                "Collector save phase started",
+                context={"task_id": task_id, "snapshot_id": snapshot_id, "transformed_count": len(data)},
+            )
             records_count = await self._save_data(db, data, task_id=task_id, snapshot_id=snapshot_id)
+            await self._log_collection_event(
+                "collector.phase.saving.success",
+                "Collector save phase completed",
+                context={
+                    "task_id": task_id,
+                    "snapshot_id": snapshot_id,
+                    "saved_count": records_count,
+                    **self._last_save_summary,
+                    "duration_ms": self._duration_ms(phase_started_at),
+                },
+            )
 
             task.status = "success"
             task.phase = "completed"
@@ -324,6 +405,20 @@ class BaseCollector(ABC):
             task.completed_at = datetime.now(UTC)
             await db.commit()
             await self._publish_task_update(force=True)
+            await self._log_collection_event(
+                "collector.run.completed",
+                "Collector run completed",
+                context={
+                    "status": "success",
+                    "task_id": task_id,
+                    "snapshot_id": snapshot_id,
+                    "raw_count": len(raw_data),
+                    "transformed_count": len(data),
+                    "saved_count": records_count,
+                    **self._last_save_summary,
+                    "duration_ms": self._duration_ms(started_at),
+                },
+            )
 
             return {
                 "status": "success",
@@ -347,6 +442,17 @@ class BaseCollector(ABC):
                 )
             await db.commit()
             await self._publish_task_update(force=True)
+            await self._log_collection_event(
+                "collector.run.cancelled",
+                "Collector run cancelled",
+                level="warning",
+                context={
+                    "status": "cancelled",
+                    "task_id": task_id,
+                    "snapshot_id": snapshot_id,
+                    "duration_ms": self._duration_ms(started_at),
+                },
+            )
             raise
         except Exception as e:
             await db.rollback()
@@ -363,6 +469,20 @@ class BaseCollector(ABC):
                     snapshot.summary = {"error": str(e)}
             await db.commit()
             await self._publish_task_update(force=True)
+            await self._log_collection_event(
+                "collector.run.failed",
+                "Collector run failed",
+                level="error",
+                context=exception_context(
+                    e,
+                    {
+                        "status": "failed",
+                        "task_id": task_id,
+                        "snapshot_id": snapshot_id,
+                        "duration_ms": self._duration_ms(started_at),
+                    },
+                ),
+            )
 
             return {
                 "status": "failed",
@@ -383,6 +503,7 @@ class BaseCollector(ABC):
         from app.models.data_snapshot import DataSnapshot
 
         if not data:
+            self._last_save_summary = {"created": 0, "updated": 0, "unchanged": 0, "deleted": 0}
             if snapshot_id is not None:
                 snapshot = await db.get(DataSnapshot, snapshot_id)
                 if snapshot:
@@ -405,7 +526,7 @@ class BaseCollector(ABC):
             select(CollectedData)
             .where(
                 CollectedData.source == self.name,
-                CollectedData.is_current == True,
+                CollectedData.is_current.is_(True),
             )
             .order_by(CollectedData.entity_key.asc(), CollectedData.collected_at.desc().nullslast(), CollectedData.id.desc())
         )
@@ -529,11 +650,51 @@ class BaseCollector(ABC):
                     "unchanged": unchanged_count,
                     "deleted": len(deleted_keys),
                 }
+            self._last_save_summary = {
+                "created": created_count,
+                "updated": updated_count,
+                "unchanged": unchanged_count,
+                "deleted": len(deleted_keys),
+            }
+        else:
+            self._last_save_summary = {
+                "created": created_count,
+                "updated": updated_count,
+                "unchanged": unchanged_count,
+                "deleted": 0,
+            }
 
         await db.commit()
         await self.update_progress(len(data), force=True)
         return records_added
 
+    @staticmethod
+    def _duration_ms(started_at: float) -> int:
+        return int((perf_counter() - started_at) * 1000)
+
+    async def _log_collection_event(
+        self,
+        event: str,
+        message: str,
+        *,
+        level: str = "info",
+        context: Dict[str, Any] | None = None,
+    ) -> None:
+        await emit_business_log(
+            logger,
+            event=event,
+            message=message,
+            category="collector",
+            level=level,
+            service="collector",
+            module=__name__,
+            context={
+                "collector_name": self.name,
+                "datasource_id": getattr(self, "_datasource_id", None),
+                **(context or {}),
+            },
+        )
+
     async def save(self, db: AsyncSession, data: List[Dict[str, Any]]) -> int:
         """Save data to database (legacy method, use _save_data instead)"""
         return await self._save_data(db, data)
@@ -546,10 +707,65 @@ class HTTPCollector(BaseCollector):
     headers: Dict[str, str] = {}
 
     async def fetch(self) -> List[Dict[str, Any]]:
+        started_at = perf_counter()
+        request_host = urlparse(self.base_url).netloc
+        await emit_business_log(
+            logger,
+            event="collector.http.fetch.start",
+            message="Collector HTTP request started",
+            category="collector",
+            service="collector",
+            module=__name__,
+            context={
+                "collector_name": self.name,
+                "datasource_id": getattr(self, "_datasource_id", None),
+                "url_host": request_host,
+            },
+        )
         async with httpx.AsyncClient(timeout=60.0) as client:
-            response = await client.get(self.base_url, headers=self.headers)
-            response.raise_for_status()
-            return self.parse_response(response.json())
+            try:
+                response = await client.get(self.base_url, headers=self.headers)
+                response.raise_for_status()
+                payload = response.json()
+                parsed = self.parse_response(payload)
+                await emit_business_log(
+                    logger,
+                    event="collector.http.fetch.success",
+                    message="Collector HTTP request completed",
+                    category="collector",
+                    service="collector",
+                    module=__name__,
+                    context={
+                        "collector_name": self.name,
+                        "datasource_id": getattr(self, "_datasource_id", None),
+                        "url_host": request_host,
+                        "status_code": response.status_code,
+                        "response_bytes": len(response.content or b""),
+                        "parsed_count": len(parsed),
+                        "duration_ms": BaseCollector._duration_ms(started_at),
+                    },
+                )
+                return parsed
+            except Exception as exc:
+                await emit_business_log(
+                    logger,
+                    event="collector.http.fetch.failed",
+                    message="Collector HTTP request failed",
+                    category="collector",
+                    level="error",
+                    service="collector",
+                    module=__name__,
+                    context=exception_context(
+                        exc,
+                        {
+                            "collector_name": self.name,
+                            "datasource_id": getattr(self, "_datasource_id", None),
+                            "url_host": request_host,
+                            "duration_ms": BaseCollector._duration_ms(started_at),
+                        },
+                    ),
+                )
+                raise
 
     @abstractmethod
     def parse_response(self, response: Dict[str, Any]) -> List[Dict[str, Any]]:

backend/app/services/collectors/bgp_common.py

@@ -19,6 +19,7 @@ from app.services.bgp_collector_locations import (
 )
 from app.services.bgp_event_locations import resolve_bgp_event_geo_dict
 from app.services.bgp_incidents import create_bgp_incidents_for_anomalies
+from app.services.earth_layer_cache import invalidate_earth_layer_cache_for_source
 from app.services.bgp_detectors import (
     detect_mass_withdrawal_anomalies,
     detect_more_specific_burst_anomalies,
@@ -223,6 +224,8 @@ async def save_bgp_observations_for_batch(
 
     if created:
         await db.commit()
+        for source in {"ris_live_bgp", "bgpstream_bgp"}:
+            invalidate_earth_layer_cache_for_source(source)
 
     return created
 

backend/app/services/collectors/celestrak.py

@@ -1,15 +1,39 @@
-"""CelesTrak TLE Collector
+"""CelesTrak TLE Collector.
 
-Collects satellite TLE (Two-Line Element) data from CelesTrak.org.
-Free, no authentication required.
+Collects the full active satellite GP element set from CelesTrak.
 """
 
+import asyncio
 import json
-from typing import Dict, Any, List
+from pathlib import Path
+from time import perf_counter
+from typing import Any, Dict, List
+from urllib.parse import urlencode, urlparse
+
 import httpx
 
+from app.core.logging import get_logger
 from app.core.satellite_tle import build_tle_lines_from_elements
+from app.services.business_logs import emit_business_log, exception_context
 from app.services.collectors.base import BaseCollector
+from app.services.collectors.downloads import DownloadHTTPStatusError, ResumableFileDownloader
+
+
+logger = get_logger(__name__, service="collector")
+ACTIVE_GROUP = "active"
+FALLBACK_GROUPS = (
+    "starlink",
+    "gps-ops",
+    "galileo",
+    "glonass",
+    "beidou",
+    "leo",
+    "geo",
+    "iridium-next",
+)
+FETCH_RETRY_ATTEMPTS = 3
+FETCH_RETRY_BASE_DELAY_SECONDS = 0.8
+CELESTRAK_NOT_UPDATED_MARKER = "GP data has not updated since your last successful"
 
 
 class CelesTrakTLECollector(BaseCollector):
@@ -18,55 +42,359 @@ class CelesTrakTLECollector(BaseCollector):
     module = "L3"
     frequency_hours = 24
     data_type = "satellite_tle"
+    _downloader = ResumableFileDownloader(
+        cache_namespace="celestrak",
+        default_accept="application/json",
+    )
 
     @property
     def base_url(self) -> str:
         return self._resolved_url or ""
 
+    def _active_url(self) -> str:
+        return self._group_url(ACTIVE_GROUP)
+
+    def _group_url(self, group: str) -> str:
+        if not self.base_url:
+            raise RuntimeError("CelesTrak base URL is not configured")
+        return f"{self.base_url}?{urlencode({'GROUP': group, 'FORMAT': 'json'})}"
+
     async def fetch(self) -> List[Dict[str, Any]]:
-        satellite_groups = [
-            "starlink",
-            "gps-ops",
-            "galileo",
-            "glonass",
-            "beidou",
-            "leo",
-            "geo",
-            "iridium-next",
-        ]
+        url = self._active_url()
+        last_error: Exception | None = None
 
-        all_satellites = []
-
-        async with httpx.AsyncClient(timeout=120.0) as client:
-            for group in satellite_groups:
+        async with httpx.AsyncClient(timeout=180.0, follow_redirects=True) as client:
+            for attempt in range(1, FETCH_RETRY_ATTEMPTS + 1):
+                started_at = perf_counter()
                 try:
-                    url = f"{self.base_url}?GROUP={group}&FORMAT=json"
-                    response = await client.get(url)
+                    await emit_business_log(
+                        logger,
+                        event="collector.celestrak.download.start",
+                        message="CelesTrak active satellite download started",
+                        category="collector",
+                        service="collector",
+                        module=__name__,
+                        context={
+                            "collector_name": self.name,
+                            "datasource_id": getattr(self, "_datasource_id", None),
+                            "group": ACTIVE_GROUP,
+                            "attempt": attempt,
+                            "url_host": urlparse(url).netloc,
+                        },
+                    )
+                    body_path = await self._downloader.download_file(
+                        client,
+                        url,
+                        extension=".json",
+                        accept="application/json",
+                        progress_callback=self._report_download_progress,
+                        validate_existing=self._validate_json_file,
+                    )
+                    data = await self._load_downloaded_payload(body_path, url)
+                    await emit_business_log(
+                        logger,
+                        event="collector.celestrak.download.success",
+                        message="CelesTrak active satellite download completed",
+                        category="collector",
+                        service="collector",
+                        module=__name__,
+                        context={
+                            "collector_name": self.name,
+                            "datasource_id": getattr(self, "_datasource_id", None),
+                            "group": ACTIVE_GROUP,
+                            "attempt": attempt,
+                            "record_count": len(data),
+                            "duration_ms": self._duration_ms(started_at),
+                        },
+                    )
+                    return data
+                except DownloadHTTPStatusError as exc:
+                    if self._is_not_updated_response(exc):
+                        cached_path = self._downloader.get_cached_file(
+                            url,
+                            ".json",
+                            validate_existing=self._validate_json_file,
+                        )
+                        if cached_path is not None:
+                            data = await self._load_downloaded_payload(cached_path, url)
+                            await emit_business_log(
+                                logger,
+                                event="collector.celestrak.download.cached_not_updated",
+                                message="CelesTrak active satellite data has not changed; using cached download",
+                                category="collector",
+                                level="warning",
+                                service="collector",
+                                module=__name__,
+                                context={
+                                    "collector_name": self.name,
+                                    "datasource_id": getattr(self, "_datasource_id", None),
+                                    "group": ACTIVE_GROUP,
+                                    "attempt": attempt,
+                                    "record_count": len(data),
+                                    "duration_ms": self._duration_ms(started_at),
+                                },
+                            )
+                            return data
+                        await emit_business_log(
+                            logger,
+                            event="collector.celestrak.download.not_updated_no_cache",
+                            message="CelesTrak active satellite data has not changed; trying fallback groups",
+                            category="collector",
+                            level="warning",
+                            service="collector",
+                            module=__name__,
+                            context=exception_context(
+                                exc,
+                                {
+                                    "collector_name": self.name,
+                                    "datasource_id": getattr(self, "_datasource_id", None),
+                                    "group": ACTIVE_GROUP,
+                                    "attempt": attempt,
+                                    "duration_ms": self._duration_ms(started_at),
+                                },
+                            ),
+                        )
+                        return await self._fetch_fallback_groups(client, active_error=exc)
+                    raise
+                except Exception as exc:
+                    last_error = exc
+                    is_final_attempt = attempt >= FETCH_RETRY_ATTEMPTS
+                    await emit_business_log(
+                        logger,
+                        event=(
+                            "collector.celestrak.download.failed"
+                            if is_final_attempt
+                            else "collector.celestrak.download.retry"
+                        ),
+                        message=(
+                            "CelesTrak active satellite download failed"
+                            if is_final_attempt
+                            else "CelesTrak active satellite download will retry"
+                        ),
+                        category="collector",
+                        level="error" if is_final_attempt else "warning",
+                        service="collector",
+                        module=__name__,
+                        context=exception_context(
+                            exc,
+                            {
+                                "collector_name": self.name,
+                                "datasource_id": getattr(self, "_datasource_id", None),
+                                "group": ACTIVE_GROUP,
+                                "attempt": attempt,
+                                "duration_ms": self._duration_ms(started_at),
+                            },
+                        ),
+                    )
+                    if not is_final_attempt:
+                        await asyncio.sleep(FETCH_RETRY_BASE_DELAY_SECONDS * attempt)
 
-                    if response.status_code == 200:
-                        data = response.json()
-                        if isinstance(data, list):
-                            for item in data:
-                                if isinstance(item, dict):
-                                    item["_celestrak_group"] = group
-                            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}")
+        raise RuntimeError(f"CelesTrak active satellite download failed after retries: {last_error}")
 
-        if not all_satellites:
-            return self._get_sample_data()
+    async def _fetch_fallback_groups(
+        self,
+        client: httpx.AsyncClient,
+        *,
+        active_error: DownloadHTTPStatusError,
+    ) -> List[Dict[str, Any]]:
+        started_at = perf_counter()
+        records_by_norad: dict[str, Dict[str, Any]] = {}
+        group_counts: dict[str, int] = {}
 
-        print(f"CelesTrak: Total satellites fetched: {len(all_satellites)}")
+        await emit_business_log(
+            logger,
+            event="collector.celestrak.fallback_groups.start",
+            message="CelesTrak fallback group download started",
+            category="collector",
+            level="warning",
+            service="collector",
+            module=__name__,
+            context={
+                "collector_name": self.name,
+                "datasource_id": getattr(self, "_datasource_id", None),
+                "groups": list(FALLBACK_GROUPS),
+                "reason": "active_not_updated_without_cache",
+            },
+        )
 
-        # Return raw data - base.run() will call transform()
-        return all_satellites
+        try:
+            for group in FALLBACK_GROUPS:
+                group_url = self._group_url(group)
+                try:
+                    body_path = await self._downloader.download_file(
+                        client,
+                        group_url,
+                        extension=".json",
+                        accept="application/json",
+                        validate_existing=self._validate_json_file,
+                    )
+                except DownloadHTTPStatusError as exc:
+                    if not self._is_not_updated_response(exc):
+                        raise RuntimeError(f"CelesTrak fallback group '{group}' download failed: {exc}") from exc
+                    cached_path = self._downloader.get_cached_file(
+                        group_url,
+                        ".json",
+                        validate_existing=self._validate_json_file,
+                    )
+                    if cached_path is None:
+                        raise RuntimeError(
+                            f"CelesTrak fallback group '{group}' has not updated and no local cached copy is available"
+                        ) from exc
+                    body_path = cached_path
+
+                group_records = await self._load_downloaded_payload(
+                    body_path,
+                    group_url,
+                    query_group=group,
+                    constellation_group=group,
+                )
+                group_counts[group] = len(group_records)
+                for item in group_records:
+                    norad_cat_id = item.get("NORAD_CAT_ID")
+                    if norad_cat_id is None:
+                        continue
+                    records_by_norad.setdefault(str(norad_cat_id), item)
+        except Exception as exc:
+            await emit_business_log(
+                logger,
+                event="collector.celestrak.fallback_groups.failed",
+                message="CelesTrak fallback group download failed",
+                category="collector",
+                level="error",
+                service="collector",
+                module=__name__,
+                context=exception_context(
+                    exc,
+                    {
+                        "collector_name": self.name,
+                        "datasource_id": getattr(self, "_datasource_id", None),
+                        "groups": list(FALLBACK_GROUPS),
+                        "completed_groups": list(group_counts),
+                        "duration_ms": self._duration_ms(started_at),
+                    },
+                ),
+            )
+            raise RuntimeError(
+                "CelesTrak active data has not updated since this network's last successful download, "
+                "no active cache is available, and fallback group mode failed. Wait until CelesTrak "
+                "publishes the next GP update, restore the Planet download cache, or use Space-Track."
+            ) from active_error
+
+        records = list(records_by_norad.values())
+        if not records:
+            raise RuntimeError("CelesTrak fallback group mode produced no satellite records")
+
+        await emit_business_log(
+            logger,
+            event="collector.celestrak.fallback_groups.success",
+            message="CelesTrak fallback group download completed",
+            category="collector",
+            level="warning",
+            service="collector",
+            module=__name__,
+            context={
+                "collector_name": self.name,
+                "datasource_id": getattr(self, "_datasource_id", None),
+                "groups": list(FALLBACK_GROUPS),
+                "group_counts": group_counts,
+                "record_count": len(records),
+                "duration_ms": self._duration_ms(started_at),
+            },
+        )
+        return records
+
+    async def _load_downloaded_payload(
+        self,
+        body_path: Path,
+        url: str,
+        *,
+        query_group: str = ACTIVE_GROUP,
+        constellation_group: str | None = None,
+    ) -> List[Dict[str, Any]]:
+        try:
+            data = self._load_active_payload(body_path)
+        except RuntimeError as exc:
+            await self._log_parse_failure(exc)
+            raise
+        for item in data:
+            item["_celestrak_query_group"] = query_group
+            item["_celestrak_source_url"] = url
+            if constellation_group:
+                item["_celestrak_group"] = constellation_group
+        return data
+
+    @staticmethod
+    def _is_not_updated_response(exc: DownloadHTTPStatusError) -> bool:
+        return exc.status_code == 403 and CELESTRAK_NOT_UPDATED_MARKER in exc.body
+
+    @staticmethod
+    def _duration_ms(started_at: float) -> int:
+        return int((perf_counter() - started_at) * 1000)
+
+    async def _report_download_progress(self, downloaded: int, total: int | None) -> None:
+        if total and total > 0:
+            await self.update_phase_progress(
+                current=min(downloaded, total),
+                total=total,
+                unit="bytes",
+                message=f"正在下载 CelesTrak active 卫星数据 {downloaded}/{total} bytes",
+                commit=True,
+            )
+
+    @staticmethod
+    def _validate_json_file(path: Path) -> bool:
+        try:
+            data = json.loads(path.read_text(encoding="utf-8"))
+        except (OSError, json.JSONDecodeError, UnicodeDecodeError):
+            return False
+        return isinstance(data, list)
+
+    async def _log_parse_failure(self, exc: Exception) -> None:
+        await emit_business_log(
+            logger,
+            event="collector.celestrak.parse.failed",
+            message="CelesTrak active satellite JSON parsing failed",
+            category="collector",
+            level="error",
+            service="collector",
+            module=__name__,
+            context=exception_context(
+                exc,
+                {
+                    "collector_name": self.name,
+                    "datasource_id": getattr(self, "_datasource_id", None),
+                    "group": ACTIVE_GROUP,
+                },
+            ),
+        )
+
+    def _load_active_payload(self, path: Path) -> List[Dict[str, Any]]:
+        try:
+            raw = json.loads(path.read_text(encoding="utf-8"))
+        except (OSError, json.JSONDecodeError, UnicodeDecodeError) as exc:
+            raise RuntimeError(f"CelesTrak active payload is not valid JSON: {exc}") from exc
+        if not isinstance(raw, list):
+            raise RuntimeError("CelesTrak active payload is not a JSON array")
+
+        records: List[Dict[str, Any]] = []
+        invalid_count = 0
+        for item in raw:
+            if isinstance(item, dict) and item.get("NORAD_CAT_ID") is not None:
+                records.append(item)
+            else:
+                invalid_count += 1
+        if invalid_count:
+            raise RuntimeError(f"CelesTrak active payload contains {invalid_count} invalid record(s)")
+        if not records:
+            raise RuntimeError("CelesTrak active payload contains no satellite records")
+        return records
 
     def transform(self, raw_data: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
         transformed = []
         for item in raw_data:
+            norad_cat_id = item.get("NORAD_CAT_ID")
             tle_line1, tle_line2 = build_tle_lines_from_elements(
-                norad_cat_id=item.get("NORAD_CAT_ID"),
+                norad_cat_id=norad_cat_id,
                 epoch=item.get("EPOCH"),
                 inclination=item.get("INCLINATION"),
                 raan=item.get("RA_OF_ASC_NODE"),
@@ -75,14 +403,18 @@ class CelesTrakTLECollector(BaseCollector):
                 mean_anomaly=item.get("MEAN_ANOMALY"),
                 mean_motion=item.get("MEAN_MOTION"),
             )
+            constellation_group = self._infer_constellation_group(item)
 
             transformed.append(
                 {
+                    "source_id": str(norad_cat_id),
                     "name": item.get("OBJECT_NAME", "Unknown"),
                     "reference_date": item.get("EPOCH", ""),
                     "metadata": {
-                        "constellation_group": item.get("_celestrak_group"),
-                        "norad_cat_id": item.get("NORAD_CAT_ID"),
+                        "constellation_group": constellation_group,
+                        "celestrak_query_group": item.get("_celestrak_query_group") or ACTIVE_GROUP,
+                        "celestrak_source_url": item.get("_celestrak_source_url"),
+                        "norad_cat_id": norad_cat_id,
                         "international_designator": item.get("OBJECT_ID"),
                         "epoch": item.get("EPOCH"),
                         "mean_motion": item.get("MEAN_MOTION"),
@@ -105,6 +437,19 @@ class CelesTrakTLECollector(BaseCollector):
             )
         return transformed
 
+    @staticmethod
+    def _infer_constellation_group(item: Dict[str, Any]) -> str | None:
+        explicit_group = str(item.get("_celestrak_group") or "").strip().lower()
+        if explicit_group and explicit_group != ACTIVE_GROUP:
+            return explicit_group
+
+        name = str(item.get("OBJECT_NAME") or "").strip().upper()
+        if name.startswith("STARLINK"):
+            return "starlink"
+        if name.startswith("IRIDIUM"):
+            return "iridium-next"
+        return None
+
     def _get_sample_data(self) -> List[Dict[str, Any]]:
         return [
             {

backend/app/services/collectors/downloads.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 import hashlib
 import json
-import tempfile
+import os
 import time
 from datetime import UTC, datetime
 from pathlib import Path
@@ -17,6 +17,31 @@ ProgressCallback = Callable[[int, int | None], Awaitable[None]]
 ValidateCallback = Callable[[Path], bool]
 
 
+class DownloadHTTPStatusError(RuntimeError):
+    """HTTP status error that keeps the upstream response body for caller-specific handling."""
+
+    def __init__(self, *, url: str, status_code: int, body: str) -> None:
+        self.url = url
+        self.status_code = status_code
+        self.body = body
+        preview = body.strip().replace("\r", " ").replace("\n", " ")[:240]
+        suffix = f": {preview}" if preview else ""
+        super().__init__(f"HTTP {status_code} while downloading {url}{suffix}")
+
+
+def default_download_cache_root() -> Path:
+    configured = os.getenv("PLANET_DOWNLOAD_CACHE_DIR")
+    if configured:
+        return Path(configured).expanduser()
+    planet_cache = os.getenv("PLANET_CACHE_DIR")
+    if planet_cache:
+        return Path(planet_cache).expanduser() / "downloads"
+    xdg_cache = os.getenv("XDG_CACHE_HOME")
+    if xdg_cache:
+        return Path(xdg_cache).expanduser() / "planet" / "downloads"
+    return Path.home() / ".cache" / "planet" / "downloads"
+
+
 class ResumableFileDownloader:
     """Download files with cache validators and byte-range resume support."""
 
@@ -26,8 +51,9 @@ class ResumableFileDownloader:
         cache_namespace: str,
         user_agent: str = "Planet-Intelligence-System/1.0 (Python/collector)",
         default_accept: str = "*/*",
+        cache_root: Path | None = None,
     ) -> None:
-        self._cache_dir = Path(tempfile.gettempdir()) / "planet-download-cache" / cache_namespace
+        self._cache_dir = (cache_root or default_download_cache_root()) / cache_namespace
         self._user_agent = user_agent
         self._default_accept = default_accept
 
@@ -43,6 +69,25 @@ class ResumableFileDownloader:
         meta_path = self._cache_dir / f"{key}.meta.json"
         return final_path, part_path, meta_path
 
+    def cached_file_path(self, url: str, extension: str) -> Path:
+        final_path, _, _ = self._cache_paths(url, extension)
+        return final_path
+
+    def get_cached_file(
+        self,
+        url: str,
+        extension: str,
+        *,
+        validate_existing: ValidateCallback | None = None,
+    ) -> Path | None:
+        final_path = self.cached_file_path(url, extension)
+        if not final_path.exists():
+            return None
+        if validate_existing and not validate_existing(final_path):
+            final_path.unlink(missing_ok=True)
+            return None
+        return final_path
+
     @staticmethod
     def _load_meta(meta_path: Path) -> dict[str, Any]:
         if not meta_path.exists():
@@ -140,7 +185,9 @@ class ResumableFileDownloader:
                 if progress_callback and expected_size and expected_size > 0:
                     await progress_callback(expected_size, expected_size)
                 return final_path
-            response.raise_for_status()
+            if response.status_code >= 400:
+                body = (await response.aread()).decode("utf-8", errors="replace")
+                raise DownloadHTTPStatusError(url=url, status_code=response.status_code, body=body)
 
             if response.status_code == 206 and resume_from > 0:
                 mode = "ab"

backend/app/services/collectors/media_news_archive.py

@@ -0,0 +1,57 @@
+from __future__ import annotations
+
+from typing import Any
+
+from app.services.collectors.base import BaseCollector
+from app.services.earth_news_store import list_all_earth_news_records
+
+
+class MediaNewsArchiveCollector(BaseCollector):
+    name = "media_news_archive"
+    priority = "P2"
+    module = "L4"
+    frequency_hours = 12
+    data_type = "news_item"
+    fail_on_empty = False
+
+    async def fetch(self) -> list[dict[str, Any]]:
+        if not self._db_session:
+            return []
+
+        records = await list_all_earth_news_records(self._db_session)
+        items: list[dict[str, Any]] = []
+        for record in records:
+            location_meta = dict(record.location_meta or {})
+            target = location_meta.get("target") if isinstance(location_meta.get("target"), dict) else {}
+            country = target.get("country")
+            city = target.get("city")
+            items.append(
+                {
+                    "id": record.id,
+                    "source_id": record.id,
+                    "name": record.title,
+                    "title": record.title,
+                    "description": record.summary,
+                    "country": country,
+                    "city": city,
+                    "latitude": record.latitude,
+                    "longitude": record.longitude,
+                    "reference_date": record.published_at,
+                    "metadata": {
+                        "url": record.url,
+                        "source": record.source,
+                        "feed_name": record.feed_name,
+                        "region": record.region,
+                        "homepage_url": record.homepage_url,
+                        "published_at": record.published_at.isoformat() if record.published_at else None,
+                        "location_label": record.location_label,
+                        "location_source": record.location_source,
+                        "verified": record.verified,
+                        "location_meta": location_meta,
+                        "first_seen_at": record.first_seen_at.isoformat() if record.first_seen_at else None,
+                        "last_seen_at": record.last_seen_at.isoformat() if record.last_seen_at else None,
+                        "resolved_at": record.resolved_at.isoformat() if record.resolved_at else None,
+                    },
+                }
+            )
+        return items

backend/app/services/collectors/telegeography.py

@@ -163,32 +163,64 @@ class TeleGeographyLandingPointCollector(BaseCollector):
     data_type = "landing_point"
 
     async def fetch(self) -> List[Dict[str, Any]]:
-        """Fetch landing point data from GitHub mirror"""
-        url = self._resolved_url or ""
+        """Fetch landing point data, falling back when the old mirror disappears."""
+        config = get_data_sources_config()
+        sources = [
+            self._resolved_url or "",
+            str(config.get_yaml_value("telegeography.landing_point_url") or ""),
+            str(config.get_yaml_value("arcgis.landing_point_url") or ""),
+        ]
 
-        async with httpx.AsyncClient(timeout=60.0) as client:
-            response = await client.get(url)
-            response.raise_for_status()
-            return self.parse_response(response.json())
+        last_error: Exception | None = None
+        async with httpx.AsyncClient(timeout=60.0, follow_redirects=True) as client:
+            for url in dict.fromkeys(source for source in sources if source):
+                try:
+                    params = (
+                        {"where": "1=1", "outFields": "*", "returnGeometry": "true", "f": "geojson"}
+                        if "FeatureServer" in url or url.endswith("/query")
+                        else None
+                    )
+                    response = await client.get(url, params=params)
+                    response.raise_for_status()
+                    records = self.parse_response(response.json())
+                    if records:
+                        return records
+                except Exception as exc:
+                    last_error = exc
+                    continue
 
-    def parse_response(self, data: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+        if last_error:
+            raise last_error
+        return self._get_sample_data()
+
+    def parse_response(self, data: List[Dict[str, Any]] | Dict[str, Any]) -> List[Dict[str, Any]]:
         """Parse landing point data"""
         result = []
+        items = data.get("features", []) if isinstance(data, dict) else data
 
-        for item in data:
+        for item in items:
+            props = item.get("properties", {}) if isinstance(item, dict) else {}
+            geometry = item.get("geometry", {}) if isinstance(item, dict) else {}
+            source = props or item
+            coords = geometry.get("coordinates", []) if isinstance(geometry, dict) else []
+            longitude = coords[0] if len(coords) > 0 else source.get("longitude")
+            latitude = coords[1] if len(coords) > 1 else source.get("latitude")
+            source_id = source.get("id") or source.get("OBJECTID") or source.get("city_id") or ""
             try:
                 entry = {
-                    "source_id": f"telegeo_lp_{item.get('id', '')}",
-                    "name": item.get("name", "Unknown"),
-                    "country": item.get("country", "Unknown"),
-                    "city": item.get("city", item.get("name", "")),
-                    "latitude": str(item.get("latitude", "")),
-                    "longitude": str(item.get("longitude", "")),
+                    "source_id": f"telegeo_lp_{source_id}",
+                    "name": source.get("name", source.get("Name", "Unknown")),
+                    "country": source.get("country", "Unknown"),
+                    "city": source.get("city", source.get("Name", source.get("name", ""))),
+                    "latitude": str(latitude or ""),
+                    "longitude": str(longitude or ""),
                     "value": "",
                     "unit": "",
                     "metadata": {
-                        "cable_count": len(item.get("cables", [])),
-                        "url": item.get("url"),
+                        "cable_count": len(source.get("cables", [])),
+                        "url": source.get("url"),
+                        "objectid": source.get("OBJECTID"),
+                        "city_id": source.get("city_id"),
                     },
                     "reference_date": datetime.now(UTC).strftime("%Y-%m-%d"),
                 }

backend/app/services/compute_center_locations.py

@@ -11,7 +11,7 @@ startup, so it must stay local and deterministic.
 
 For the full design and the reason behind the abstraction (compute centers,
 BGP collectors, BGP events, and future entities all share one pipeline),
-see ``docs/plans/location-resolver-shared-pipeline-plan.md``.
+see ``docs/technical/zh/location-pipeline-development.md``.
 
 The ``ComputeCenterLocation`` dataclass and the public function signatures are
 preserved verbatim so existing callers and tests do not need to change.
@@ -713,6 +713,30 @@ def collect_location_candidates(
     The unused ``source`` / ``source_id`` / ``record_id`` arguments are kept
     for backward compatibility with the API handler that calls this function.
     """
+    query = build_compute_center_location_query(
+        name=name,
+        source=source,
+        source_id=source_id,
+        operator=operator,
+        site=site,
+        city=city,
+        country=country,
+        organization=organization,
+    )
+    return COMPUTE_CENTER_COLLECTION_PIPELINE.collect_candidates(query)
+
+
+def build_compute_center_location_query(
+    *,
+    name: str | None = None,
+    source: str | None = None,
+    source_id: str | None = None,
+    operator: str | None = None,
+    site: str | None = None,
+    city: str | None = None,
+    country: str | None = None,
+    organization: str | None = None,
+) -> LocationQuery:
     name_value = coerce_str(name)
     context: dict[str, str] = {
         "source": coerce_str(source),
@@ -725,8 +749,7 @@ def collect_location_candidates(
         "operator": coerce_str(operator or organization),
         "organization": coerce_str(organization),
     }
-    query = _context_to_query(context)
-    return COMPUTE_CENTER_COLLECTION_PIPELINE.collect_candidates(query)
+    return _context_to_query(context)
 
 
 def _record_operator(metadata: dict[str, Any]) -> str | None:

backend/app/services/credential_guides.py

@@ -3,16 +3,22 @@
 from __future__ import annotations
 
 from dataclasses import dataclass
+from copy import deepcopy
 from typing import Any
 
 from sqlalchemy import select
+from sqlalchemy.orm.attributes import flag_modified
 
+from app.ai_tasks.prompts import get_effective_prompt
 from app.models.system_setting import SystemSetting
 from app.schemas.ai import SituationalAnalysisRequest
 from app.services.ai_client import AIProviderClient
+from app.services.ai_tools.evidence_store import normalize_search_evidence
+from app.services.ai_tools.web_search import WebSearchClient, WebSearchError
 
 
 CREDENTIAL_GUIDES_CATEGORY = "collector_credential_guides"
+CREDENTIAL_GUIDE_PROMPT_KEY = "credential.guide"
 
 
 @dataclass(frozen=True)
@@ -131,59 +137,101 @@ DEFAULT_CREDENTIAL_GUIDES = {
 }
 
 
+def _normalize_provider(provider: str) -> str:
+    return provider.strip().lower().replace(" ", "_")
+
+
+def _credential_guide_default(provider: str) -> CredentialGuideDefault:
+    normalized = _normalize_provider(provider)
+    known = DEFAULT_CREDENTIAL_GUIDES.get(normalized)
+    if known is not None:
+        return known
+    title = f"{normalized or 'collector'} 凭证配置教程"
+    return CredentialGuideDefault(
+        provider=normalized,
+        title=title,
+        prompt=(
+            f"请生成一份中文教程，指导开发者为 Planet 采集器配置 {normalized} 凭证。"
+            "教程要面向已经有本地开发环境的人，包含官方入口或文档查找方式、"
+            "获取 API Key / Token / Client credentials 的通用步骤、在 Planet 采集器配置中"
+            "填写凭证字段、连接测试、保存、常见失败排查。不要编造具体页面按钮文案；"
+            "如果公开资料不足，必须明确提醒以 provider 官方文档和当前控制台页面为准。"
+        ),
+        markdown="",
+    )
+
+
 async def _get_guide_store(db) -> tuple[SystemSetting | None, dict[str, Any]]:
     result = await db.execute(
         select(SystemSetting).where(SystemSetting.category == CREDENTIAL_GUIDES_CATEGORY)
     )
     record = result.scalar_one_or_none()
-    payload = dict(record.payload or {}) if record and isinstance(record.payload, dict) else {}
+    payload = deepcopy(record.payload) if record and isinstance(record.payload, dict) else {}
     return record, payload
 
 
 async def get_credential_guide(db, provider: str) -> dict[str, Any]:
-    default = DEFAULT_CREDENTIAL_GUIDES.get(provider)
-    if default is None:
-        raise ValueError(f"Unsupported credential guide provider: {provider}")
+    provider = _normalize_provider(provider)
+    default = _credential_guide_default(provider)
 
     _record, store = await _get_guide_store(db)
     custom = store.get(provider) if isinstance(store.get(provider), dict) else None
+    has_default_markdown = bool(default.markdown.strip())
     return {
         "provider": provider,
         "title": custom.get("title") if custom else default.title,
         "markdown": custom.get("markdown") if custom else default.markdown,
         "prompt": default.prompt,
-        "source": "ai" if custom else "default",
+        "source": "ai" if custom else "default" if has_default_markdown else "missing",
+        "sources": custom.get("sources", []) if custom else [],
+        "verification_status": (
+            custom.get("verification_status", "verified_with_search_evidence")
+            if custom
+            else "default_unverified" if has_default_markdown else "missing"
+        ),
+        "verification_error": custom.get("verification_error") if custom else None,
     }
 
 
-async def save_credential_guide(db, provider: str, title: str, markdown: str) -> dict[str, Any]:
-    default = DEFAULT_CREDENTIAL_GUIDES.get(provider)
-    if default is None:
-        raise ValueError(f"Unsupported credential guide provider: {provider}")
+async def save_credential_guide(
+    db,
+    provider: str,
+    title: str,
+    markdown: str,
+    *,
+    sources: list[dict[str, Any]] | None = None,
+    verification_status: str = "verified_with_search_evidence",
+    verification_error: str | None = None,
+) -> dict[str, Any]:
+    provider = _normalize_provider(provider)
+    default = _credential_guide_default(provider)
 
     record, store = await _get_guide_store(db)
     store[provider] = {
         "title": title or default.title,
         "markdown": markdown,
+        "sources": sources or [],
+        "verification_status": verification_status,
+        "verification_error": verification_error,
     }
     if record is None:
         db.add(SystemSetting(category=CREDENTIAL_GUIDES_CATEGORY, payload=store))
     else:
-        record.payload = store
+        record.payload = deepcopy(store)
+        flag_modified(record, "payload")
     await db.commit()
     return await get_credential_guide(db, provider)
 
 
 async def reset_credential_guide(db, provider: str) -> dict[str, Any]:
-    default = DEFAULT_CREDENTIAL_GUIDES.get(provider)
-    if default is None:
-        raise ValueError(f"Unsupported credential guide provider: {provider}")
+    provider = _normalize_provider(provider)
 
     record, store = await _get_guide_store(db)
     if provider in store:
         store.pop(provider, None)
         if record is not None:
-            record.payload = store
+            record.payload = deepcopy(store)
+            flag_modified(record, "payload")
             await db.commit()
     return await get_credential_guide(db, provider)
 
@@ -192,28 +240,55 @@ async def generate_credential_guide(
     db,
     provider: str,
     ai_client: AIProviderClient,
+    web_search_client: WebSearchClient | None = None,
 ) -> dict[str, Any]:
-    default = DEFAULT_CREDENTIAL_GUIDES.get(provider)
-    if default is None:
-        raise ValueError(f"Unsupported credential guide provider: {provider}")
+    provider = _normalize_provider(provider)
+    default = _credential_guide_default(provider)
 
+    search_evidence: list[dict[str, Any]] = []
+    search_error: str | None = None
+    if web_search_client is not None:
+        try:
+            evidence = await web_search_client.search(
+                _credential_guide_search_query(default),
+                max_results=5,
+            )
+            search_evidence = normalize_search_evidence(evidence, limit=5)
+        except WebSearchError as exc:
+            search_error = str(exc)
+        except Exception as exc:
+            search_error = f"WebSearch unavailable: {exc}"
+
+    if not search_evidence:
+        guide = await get_credential_guide(db, provider)
+        guide["verification_status"] = "unverified_no_search_evidence"
+        guide["verification_error"] = search_error
+        guide["sources"] = []
+        return guide
+
+    prompt = await get_effective_prompt(db, CREDENTIAL_GUIDE_PROMPT_KEY)
     response = await ai_client.analyze(
         SituationalAnalysisRequest(
             title=f"Generate credential guide for {provider}",
-            objective=default.prompt,
+            objective=f"{default.prompt}\n{prompt.prompt}",
+            system_prompt=prompt.system_prompt or None,
             context={
                 "provider": provider,
                 "current_default_guide": default.markdown,
                 "product_context": "Planet collector credential settings",
+                "search_evidence": search_evidence,
             },
             observations=[
                 "Use concise Chinese markdown.",
                 "Prefer stable concepts over brittle UI labels.",
                 "Include verification and troubleshooting steps.",
+                "Include a short sources section with the provided URLs.",
             ],
             constraints=[
                 "Do not ask the user for secrets.",
                 "Do not include fabricated screenshots.",
+                "Do not invent source URLs or product UI labels.",
+                "Use only the provided search_evidence as factual support.",
                 "Return markdown only.",
             ],
         )
@@ -221,4 +296,19 @@ async def generate_credential_guide(
     markdown = response.content.strip()
     if not markdown:
         markdown = default.markdown
-    return await save_credential_guide(db, provider, default.title, markdown)
+    return await save_credential_guide(
+        db,
+        provider,
+        default.title,
+        markdown,
+        sources=search_evidence,
+        verification_status="verified_with_search_evidence",
+    )
+
+
+def _credential_guide_search_query(default: CredentialGuideDefault) -> str:
+    if default.provider == "barentswatch":
+        return "BarentsWatch developer tutorial AIS API OAuth client credentials"
+    if default.provider == "aisstream":
+        return "AISStream API key documentation websocket stream"
+    return f"{default.provider} API credentials documentation"

backend/app/services/data_jobs.py

@@ -0,0 +1,597 @@
+"""Kafka-ready datasource job queue backed by PostgreSQL for v1."""
+
+from __future__ import annotations
+
+import asyncio
+from datetime import UTC, datetime, timedelta
+from uuid import uuid4
+from typing import Any
+
+from sqlalchemy import bindparam, select, text
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.core.cache import cache
+from app.core.config import settings
+from app.core.logging import get_logger
+from app.core.time import to_iso8601_utc
+from app.core.websocket.broadcaster import broadcaster
+from app.db.session import async_session_factory
+from app.models.collected_data import CollectedData
+from app.models.data_snapshot import DataSnapshot
+from app.models.datasource import DataSource
+from app.models.task import CollectionTask
+from app.services.collectors.registry import collector_registry
+from app.services.datasource_connectivity import (
+    build_builtin_connectivity_checksum,
+    get_builtin_effective_candidate,
+    save_connectivity_success,
+)
+from app.services.earth_layer_adapters import (
+    clear_derived_datasource_data,
+    get_earth_refresh_strategy_for_change,
+    get_earth_update_layers_for_source,
+)
+from app.services.earth_layer_cache import invalidate_earth_layer_cache_for_source
+from app.services.scheduler import sync_datasource_job
+
+logger = get_logger(__name__)
+
+JOB_TYPE_COLLECT = "collect"
+JOB_TYPE_CLEAR_DATA = "clear_data"
+JOB_TYPE_CLEAR_CACHE = "clear_cache"
+JOB_TYPE_EARTH_REFRESH = "earth_refresh"
+
+JOB_STATUS_QUEUED = "queued"
+JOB_STATUS_RUNNING = "running"
+JOB_STATUS_CANCELLING = "cancelling"
+JOB_STATUS_SUCCESS = "success"
+JOB_STATUS_FAILED = "failed"
+JOB_STATUS_CANCELLED = "cancelled"
+
+ACTIVE_JOB_STATUSES = (JOB_STATUS_QUEUED, JOB_STATUS_RUNNING, JOB_STATUS_CANCELLING)
+TERMINAL_JOB_STATUSES = (JOB_STATUS_SUCCESS, JOB_STATUS_FAILED, JOB_STATUS_CANCELLED)
+DATA_WRITE_JOB_TYPES = (JOB_TYPE_COLLECT, JOB_TYPE_CLEAR_DATA, JOB_TYPE_CLEAR_CACHE)
+SOURCE_LOCK_JOB_STATUSES = (JOB_STATUS_RUNNING, JOB_STATUS_CANCELLING)
+QUEUE_POLL_SECONDS = 0.35
+JOB_STALE_LOCK_MINUTES = 90
+DEFAULT_WORKER_CONCURRENCY = 2
+
+RUNNING_DATA_JOB_TASKS: dict[int, asyncio.Task[Any]] = {}
+
+
+def _utcnow() -> datetime:
+    return datetime.now(UTC)
+
+
+def _job_worker_id() -> str:
+    return f"{settings.PROJECT_NAME}:data-job-worker:{uuid4().hex[:8]}"
+
+
+def is_terminal_job_status(status: str | None) -> bool:
+    return status in TERMINAL_JOB_STATUSES
+
+
+async def enqueue_datasource_job(
+    db: AsyncSession,
+    datasource: DataSource,
+    task_type: str,
+    *,
+    payload: dict[str, Any] | None = None,
+    rollback_policy: str = "keep_committed_batches",
+    dedupe_key: str | None = None,
+) -> CollectionTask:
+    if dedupe_key:
+        existing = await _get_active_job_by_dedupe_key(db, dedupe_key)
+        if existing is not None:
+            return existing
+
+    task = CollectionTask(
+        datasource_id=datasource.id,
+        source=datasource.source,
+        task_type=task_type,
+        status=JOB_STATUS_QUEUED,
+        phase="queued",
+        phase_message="任务已进入队列",
+        payload=payload or {},
+        rollback_policy=rollback_policy,
+        dedupe_key=dedupe_key,
+    )
+    db.add(task)
+    await db.commit()
+    await db.refresh(task)
+    await _broadcast_task_update(task)
+    return task
+
+
+async def enqueue_earth_refresh_job(
+    db: AsyncSession,
+    *,
+    source: str,
+    payload: dict[str, Any] | None = None,
+) -> CollectionTask | None:
+    layers = list((payload or {}).get("layers") or get_earth_update_layers_for_source(source))
+    if not layers:
+        return None
+
+    datasource = await _get_or_create_virtual_datasource(db, source)
+    refresh_payload = {
+        "source": source,
+        "layers": layers,
+        "refresh_strategy": (payload or {}).get("refresh_strategy")
+        or get_earth_refresh_strategy_for_change((payload or {}).get("table"), source)
+        or "clear_then_reload",
+        **(payload or {}),
+    }
+    return await enqueue_datasource_job(
+        db,
+        datasource,
+        JOB_TYPE_EARTH_REFRESH,
+        payload=refresh_payload,
+        dedupe_key=f"earth_refresh:{source}",
+    )
+
+
+async def enqueue_earth_refresh_from_update(payload: dict[str, Any]) -> None:
+    source = str(payload.get("source") or "").strip()
+    if not source:
+        return
+    async with async_session_factory() as db:
+        await enqueue_earth_refresh_job(db, source=source, payload=payload)
+
+
+async def request_cancel_datasource_task(
+    db: AsyncSession,
+    task: CollectionTask,
+    *,
+    reason: str = "cancelled_by_operator",
+) -> CollectionTask:
+    if is_terminal_job_status(task.status):
+        return task
+
+    running_task = RUNNING_DATA_JOB_TASKS.get(task.id)
+    if task.status == JOB_STATUS_QUEUED or (
+        running_task is None
+        and (
+            task.status == JOB_STATUS_CANCELLING
+            or (task.status == JOB_STATUS_RUNNING and task.task_type != JOB_TYPE_COLLECT)
+        )
+    ):
+        return await _cancel_task_without_runner(db, task, reason=reason)
+
+    task.status = JOB_STATUS_CANCELLING
+    task.phase = JOB_STATUS_CANCELLING
+    task.phase_message = "正在停止任务"
+    task.requested_cancel_at = _utcnow()
+    task.cancel_reason = reason
+    await db.commit()
+    await db.refresh(task)
+
+    if running_task is not None and not running_task.done():
+        running_task.cancel()
+
+    await _broadcast_task_update(task)
+    return task
+
+
+async def _cancel_task_without_runner(
+    db: AsyncSession,
+    task: CollectionTask,
+    *,
+    reason: str,
+) -> CollectionTask:
+    if task.task_type == JOB_TYPE_COLLECT:
+        await db.execute(CollectedData.__table__.delete().where(CollectedData.task_id == task.id))
+        snapshot_result = await db.execute(select(DataSnapshot).where(DataSnapshot.task_id == task.id))
+        for snapshot in snapshot_result.scalars().all():
+            snapshot.status = JOB_STATUS_CANCELLED
+            snapshot.completed_at = _utcnow()
+            snapshot.error_message = "Cancelled after operator stop request; no active worker handle remained"
+        datasource = await db.get(DataSource, task.datasource_id)
+        if datasource is not None:
+            datasource.last_status = JOB_STATUS_CANCELLED
+
+    task.status = JOB_STATUS_CANCELLED
+    task.phase = JOB_STATUS_CANCELLED
+    task.phase_message = "任务已停止"
+    task.completed_at = _utcnow()
+    task.requested_cancel_at = task.requested_cancel_at or _utcnow()
+    task.cancel_reason = reason
+    await db.commit()
+    await db.refresh(task)
+    await _broadcast_task_update(task)
+    return task
+
+
+async def get_active_datasource_job(
+    db: AsyncSession,
+    datasource_id: int,
+    *,
+    task_types: tuple[str, ...] = DATA_WRITE_JOB_TYPES,
+) -> CollectionTask | None:
+    result = await db.execute(
+        select(CollectionTask)
+        .where(CollectionTask.datasource_id == datasource_id)
+        .where(CollectionTask.task_type.in_(task_types))
+        .where(CollectionTask.status.in_(ACTIVE_JOB_STATUSES))
+        .order_by(CollectionTask.created_at.desc().nullslast(), CollectionTask.id.desc())
+        .limit(1)
+    )
+    return result.scalar_one_or_none()
+
+
+async def _get_active_job_by_dedupe_key(db: AsyncSession, dedupe_key: str) -> CollectionTask | None:
+    result = await db.execute(
+        select(CollectionTask)
+        .where(CollectionTask.dedupe_key == dedupe_key)
+        .where(CollectionTask.status.in_(ACTIVE_JOB_STATUSES))
+        .order_by(CollectionTask.created_at.desc().nullslast(), CollectionTask.id.desc())
+        .limit(1)
+    )
+    return result.scalar_one_or_none()
+
+
+async def _get_or_create_virtual_datasource(db: AsyncSession, source: str) -> DataSource:
+    result = await db.execute(select(DataSource).where(DataSource.source == source))
+    datasource = result.scalar_one_or_none()
+    if datasource is not None:
+        return datasource
+
+    datasource = DataSource(
+        name=f"Earth refresh: {source}",
+        source=source,
+        module="SYS",
+        collector_class="EarthRefreshJob",
+        is_active=True,
+    )
+    db.add(datasource)
+    await db.commit()
+    await db.refresh(datasource)
+    return datasource
+
+
+async def _broadcast_task_update(task: CollectionTask) -> None:
+    await broadcaster.broadcast_datasource_task_update(
+        {
+            "datasource_id": task.datasource_id,
+            "collector_name": task.source,
+            "task_id": task.id,
+            "task_type": task.task_type,
+            "status": task.status,
+            "phase": task.phase,
+            "phase_progress": task.phase_progress,
+            "phase_message": task.phase_message,
+            "phase_current": task.phase_current,
+            "phase_total": task.phase_total,
+            "phase_unit": task.phase_unit,
+            "progress": task.progress,
+            "records_processed": task.records_processed,
+            "total_records": task.total_records,
+            "started_at": to_iso8601_utc(task.started_at),
+            "completed_at": to_iso8601_utc(task.completed_at),
+            "requested_cancel_at": to_iso8601_utc(task.requested_cancel_at),
+            "error_message": task.error_message,
+        }
+    )
+
+
+class DataJobWorker:
+    def __init__(self, *, concurrency: int = DEFAULT_WORKER_CONCURRENCY) -> None:
+        self.worker_id = _job_worker_id()
+        self.concurrency = max(1, concurrency)
+        self._task: asyncio.Task[None] | None = None
+        self._stop_event: asyncio.Event | None = None
+        self._running: set[asyncio.Task[Any]] = set()
+
+    def start(self) -> None:
+        if self._task and not self._task.done():
+            return
+        self._stop_event = asyncio.Event()
+        self._task = asyncio.create_task(self._run(), name="data-job-worker")
+
+    async def stop(self) -> None:
+        if self._stop_event:
+            self._stop_event.set()
+        for task in list(self._running):
+            task.cancel()
+        if self._task:
+            await asyncio.gather(self._task, return_exceptions=True)
+        if self._running:
+            await asyncio.gather(*self._running, return_exceptions=True)
+
+    async def _run(self) -> None:
+        assert self._stop_event is not None
+        await self._recover_stale_running_jobs()
+        while not self._stop_event.is_set():
+            self._running = {task for task in self._running if not task.done()}
+            if len(self._running) >= self.concurrency:
+                await asyncio.sleep(QUEUE_POLL_SECONDS)
+                continue
+
+            task_id = await self._claim_next_job()
+            if task_id is None:
+                await asyncio.sleep(QUEUE_POLL_SECONDS)
+                continue
+
+            runner = asyncio.create_task(self._run_claimed_job(task_id), name=f"data-job:{task_id}")
+            self._running.add(runner)
+
+    async def _recover_stale_running_jobs(self) -> None:
+        cutoff = _utcnow() - timedelta(minutes=JOB_STALE_LOCK_MINUTES)
+        async with async_session_factory() as db:
+            result = await db.execute(
+                select(CollectionTask)
+                .where(CollectionTask.status.in_((JOB_STATUS_RUNNING, JOB_STATUS_CANCELLING)))
+                .where(CollectionTask.locked_at.is_not(None))
+                .where(CollectionTask.locked_at < cutoff)
+            )
+            stale_jobs = list(result.scalars().all())
+            for job in stale_jobs:
+                job.status = JOB_STATUS_FAILED
+                job.phase = JOB_STATUS_FAILED
+                job.completed_at = _utcnow()
+                job.error_message = "Marked failed after stale data job lock timeout"
+            if stale_jobs:
+                await db.commit()
+
+    async def _claim_next_job(self) -> int | None:
+        async with async_session_factory() as db:
+            row = await db.execute(
+                text(
+                    """
+                    SELECT queued.id
+                    FROM collection_tasks AS queued
+                    WHERE queued.status = :queued_status
+                      AND NOT EXISTS (
+                        SELECT 1
+                        FROM collection_tasks AS active
+                        WHERE active.source = queued.source
+                          AND active.id <> queued.id
+                          AND active.status IN :active_statuses
+                      )
+                    ORDER BY queued.created_at ASC NULLS FIRST, queued.id ASC
+                    LIMIT 1
+                    FOR UPDATE SKIP LOCKED
+                    """
+                ).bindparams(bindparam("active_statuses", expanding=True)),
+                {
+                    "queued_status": JOB_STATUS_QUEUED,
+                    "active_statuses": SOURCE_LOCK_JOB_STATUSES,
+                },
+            )
+            task_id = row.scalar_one_or_none()
+            if task_id is None:
+                return None
+
+            task = await db.get(CollectionTask, int(task_id))
+            if task is None:
+                return None
+            task.status = JOB_STATUS_RUNNING
+            task.phase = "starting"
+            task.phase_message = "任务开始执行"
+            task.started_at = task.started_at or _utcnow()
+            task.worker_id = self.worker_id
+            task.locked_at = _utcnow()
+            await db.commit()
+            await _broadcast_task_update(task)
+            return int(task_id)
+
+    async def _run_claimed_job(self, task_id: int) -> None:
+        current_task = asyncio.current_task()
+        if current_task is not None:
+            RUNNING_DATA_JOB_TASKS[task_id] = current_task
+        try:
+            async with async_session_factory() as db:
+                task = await db.get(CollectionTask, task_id)
+                if task is None:
+                    return
+                await self._execute_job(db, task)
+        except asyncio.CancelledError:
+            async with async_session_factory() as db:
+                task = await db.get(CollectionTask, task_id)
+                if task is not None and not is_terminal_job_status(task.status):
+                    task.status = JOB_STATUS_CANCELLED
+                    task.phase = JOB_STATUS_CANCELLED
+                    task.phase_message = "任务已停止"
+                    task.completed_at = _utcnow()
+                    await db.commit()
+                    await _broadcast_task_update(task)
+            raise
+        except Exception as exc:
+            logger.exception_event(
+                "Data job failed",
+                event="data_jobs.job_failed",
+                context={"task_id": task_id, "error": str(exc)},
+            )
+            async with async_session_factory() as db:
+                task = await db.get(CollectionTask, task_id)
+                if task is not None:
+                    task.status = JOB_STATUS_FAILED
+                    task.phase = JOB_STATUS_FAILED
+                    task.phase_message = str(exc)
+                    task.error_message = str(exc)
+                    task.completed_at = _utcnow()
+                    await db.commit()
+                    await _broadcast_task_update(task)
+        finally:
+            RUNNING_DATA_JOB_TASKS.pop(task_id, None)
+
+    async def _execute_job(self, db: AsyncSession, task: CollectionTask) -> None:
+        if task.task_type == JOB_TYPE_COLLECT:
+            await _run_collect_job(db, task)
+        elif task.task_type == JOB_TYPE_CLEAR_DATA:
+            await _run_clear_data_job(db, task)
+        elif task.task_type == JOB_TYPE_CLEAR_CACHE:
+            await _run_clear_cache_job(db, task)
+        elif task.task_type == JOB_TYPE_EARTH_REFRESH:
+            await _run_earth_refresh_job(db, task)
+        else:
+            raise RuntimeError(f"Unsupported data job type: {task.task_type}")
+
+
+async def _run_collect_job(db: AsyncSession, task: CollectionTask) -> None:
+    datasource = await db.get(DataSource, task.datasource_id)
+    if datasource is None:
+        raise RuntimeError("Data source not found")
+
+    collector = collector_registry.get(datasource.source)
+    if collector is None:
+        raise RuntimeError(f"Collector '{datasource.source}' not found")
+    if not datasource.is_active:
+        raise RuntimeError("Data source is disabled")
+
+    collector._datasource_id = datasource.id
+    collector._current_task = task
+    collector._db_session = db
+    result = await collector.run(db)
+
+    datasource.last_run_at = _utcnow()
+    datasource.last_status = result.get("status")
+    if datasource.last_status == JOB_STATUS_SUCCESS:
+        effective_candidate = await get_builtin_effective_candidate(db, datasource.source)
+        checksum, _credential_context = await build_builtin_connectivity_checksum(
+            datasource.source,
+            effective_candidate["endpoint"],
+            effective_candidate["auth_type"],
+            effective_candidate["headers"],
+            effective_candidate["config"],
+            db,
+        )
+        await save_connectivity_success(
+            db,
+            datasource.source,
+            checksum,
+            {"status_code": None},
+            connected_by="collection",
+        )
+    await db.commit()
+    await sync_datasource_job(datasource.id)
+
+
+async def _run_clear_data_job(db: AsyncSession, task: CollectionTask) -> None:
+    source = str(task.source or (task.payload or {}).get("source") or "").strip()
+    if not source:
+        raise RuntimeError("Clear data job has no source")
+
+    task.phase = "clearing_data"
+    task.phase_message = "正在删除数据库数据"
+    await db.commit()
+    await _broadcast_task_update(task)
+
+    count_result = await db.execute(
+        select(CollectedData.id).where(CollectedData.source == source)
+    )
+    collected_ids = [row[0] for row in count_result.all()]
+    derived_deleted_counts = await clear_derived_datasource_data(db, source)
+    if collected_ids:
+        await db.execute(CollectedData.__table__.delete().where(CollectedData.id.in_(collected_ids)))
+    deleted_count = len(collected_ids)
+    derived_deleted_count = sum(derived_deleted_counts.values())
+
+    task.records_processed = deleted_count + derived_deleted_count
+    task.total_records = task.records_processed
+    task.progress = 100.0
+    task.phase_progress = 100.0
+    task.phase_current = task.records_processed
+    task.phase_total = task.records_processed
+    task.phase_unit = "records"
+    task.payload = {
+        **(task.payload or {}),
+        "deleted_count": deleted_count,
+        "derived_deleted_count": derived_deleted_count,
+        "derived_deleted_counts": derived_deleted_counts,
+    }
+    task.status = JOB_STATUS_SUCCESS
+    task.phase = "completed"
+    task.phase_message = "数据库数据已清理"
+    task.completed_at = _utcnow()
+    await db.commit()
+    await _broadcast_task_update(task)
+
+
+async def _run_clear_cache_job(db: AsyncSession, task: CollectionTask) -> None:
+    source = str(task.source or (task.payload or {}).get("source") or "").strip()
+    if not source:
+        raise RuntimeError("Clear cache job has no source")
+
+    earth_deleted_count = invalidate_earth_layer_cache_for_source(source)
+    dashboard_deleted_count = int(cache.delete("dashboard:stats")) + int(cache.delete("dashboard:summary"))
+    deleted_count = earth_deleted_count + dashboard_deleted_count
+
+    task.records_processed = deleted_count
+    task.total_records = deleted_count
+    task.progress = 100.0
+    task.phase_progress = 100.0
+    task.phase = "completed"
+    task.phase_message = "缓存已清理"
+    task.payload = {
+        **(task.payload or {}),
+        "earth_layer_deleted_count": earth_deleted_count,
+        "dashboard_deleted_count": dashboard_deleted_count,
+    }
+    task.status = JOB_STATUS_SUCCESS
+    task.completed_at = _utcnow()
+    await db.commit()
+    await _broadcast_task_update(task)
+    await enqueue_earth_refresh_job(db, source=source, payload={"operation": "CACHE_INVALIDATED"})
+
+
+async def _run_earth_refresh_job(db: AsyncSession, task: CollectionTask) -> None:
+    payload = task.payload or {}
+    source = str(payload.get("source") or task.source or "").strip()
+    layers = list(payload.get("layers") or get_earth_update_layers_for_source(source))
+    if not source or not layers:
+        task.status = JOB_STATUS_SUCCESS
+        task.phase = "completed"
+        task.phase_message = "没有需要刷新的 Earth 图层"
+        task.completed_at = _utcnow()
+        await db.commit()
+        await _broadcast_task_update(task)
+        return
+
+    deleted_cache_entries = invalidate_earth_layer_cache_for_source(source)
+    update_payload = {
+        "event": "earth.layer.changed",
+        "action": "database_changed",
+        "source": source,
+        "table": payload.get("table"),
+        "data_type": source,
+        "layers": layers,
+        "refresh_strategy": payload.get("refresh_strategy") or "clear_then_reload",
+        "records_processed": payload.get("records_processed", 0),
+        "operations": payload.get("operations") or [payload.get("operation") or "CHANGE"],
+        "operation": payload.get("operation"),
+        "cache_entries_invalidated": deleted_cache_entries,
+        "timestamp": to_iso8601_utc(_utcnow()),
+    }
+    if payload.get("entity") == "interactable":
+        update_payload.update(
+            {
+                "entity": "interactable",
+                "action": payload.get("action") or "changed",
+                "ids": payload.get("ids") or payload.get("entity_keys") or [],
+                "item": payload.get("item"),
+            }
+        )
+    await broadcaster.broadcast_earth_update(update_payload)
+
+    task.records_processed = int(payload.get("records_processed") or 0)
+    task.progress = 100.0
+    task.phase_progress = 100.0
+    task.phase = "completed"
+    task.phase_message = "Earth 图层刷新通知已发送"
+    task.status = JOB_STATUS_SUCCESS
+    task.completed_at = _utcnow()
+    task.payload = {**payload, "cache_entries_invalidated": deleted_cache_entries}
+    await db.commit()
+    await _broadcast_task_update(task)
+
+
+_worker = DataJobWorker()
+
+
+def start_data_job_worker() -> None:
+    _worker.start()
+
+
+async def stop_data_job_worker() -> None:
+    await _worker.stop()

backend/app/services/datasource_connectivity.py

@@ -18,6 +18,7 @@ from app.models.datasource import DataSource
 from app.models.datasource_config import DataSourceConfig
 from app.models.system_setting import SystemSetting
 from app.services.barentswatch import (
+    BarentsWatchConfig,
     _read_zshrc_env,
     fetch_barentswatch_access_token,
     resolve_barentswatch_config,
@@ -44,6 +45,20 @@ def _resolve_spacetrack_credentials() -> tuple[str, str, str]:
     return username, password, source or "missing"
 
 
+def _resolve_spacetrack_credentials_with_override(
+    credential_override: dict[str, str] | None = None,
+) -> tuple[str, str, str]:
+    if credential_override and (
+        credential_override.get("username") or credential_override.get("password")
+    ):
+        return (
+            str(credential_override.get("username") or ""),
+            str(credential_override.get("password") or ""),
+            "draft",
+        )
+    return _resolve_spacetrack_credentials()
+
+
 async def _resolve_aisstream_api_key(
     db=None,
     credential_override: dict[str, str] | None = None,
@@ -126,7 +141,9 @@ async def build_builtin_connectivity_checksum(
             }
         )
     elif credential_provider == "spacetrack":
-        username, password, credential_source = _resolve_spacetrack_credentials()
+        username, password, credential_source = _resolve_spacetrack_credentials_with_override(
+            credential_override
+        )
         has_credentials = bool(username and password)
         credential_fingerprint = _sha256_json(
             {
@@ -230,7 +247,16 @@ async def test_builtin_connectivity(
     try:
         async with httpx.AsyncClient(timeout=timeout, follow_redirects=True) as client:
             if credential_context["credential_provider"] == "barentswatch":
-                barentswatch_config = await resolve_barentswatch_config(db)
+                if credential_override:
+                    barentswatch_config = BarentsWatchConfig(
+                        endpoint=str(request_endpoint or ""),
+                        client_id=str(credential_override.get("client_id") or ""),
+                        client_secret=str(credential_override.get("client_secret") or ""),
+                        credential_source="draft",
+                        endpoint_source="draft",
+                    )
+                else:
+                    barentswatch_config = await resolve_barentswatch_config(db)
                 token = await fetch_barentswatch_access_token(client, barentswatch_config)
                 if not token:
                     return {
@@ -243,7 +269,9 @@ async def test_builtin_connectivity(
                     }
                 request_headers["Authorization"] = f"Bearer {token}"
             elif credential_context["credential_provider"] == "spacetrack":
-                username, password, _source = _resolve_spacetrack_credentials()
+                username, password, _source = _resolve_spacetrack_credentials_with_override(
+                    credential_override
+                )
                 login_url = "https://www.space-track.org/ajaxauth/login"
                 login_response = await client.post(
                     login_url,

backend/app/services/datasource_mapping.py

@@ -8,6 +8,7 @@ import re
 from datetime import UTC, datetime
 from typing import Any
 
+from sqlalchemy import select
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.core.target_schema_registry import TargetSchema, get_target_schema
@@ -254,6 +255,12 @@ def _best_field_match(field_name: str, candidates: list[str]) -> str | None:
         "lat": ("lat", "latitude", "y"),
         "lon": ("lon", "lng", "longitude", "x"),
         "mmsi": ("mmsi",),
+        "geometry": ("geometry", "geom"),
+        "properties": ("properties", "props"),
+        "source_kind": ("source_kind", "kind", "type"),
+        "feature_count": ("feature_count", "features_count", "count"),
+        "artifact_path": ("artifact_path", "path", "file"),
+        "sha256": ("sha256", "hash", "checksum"),
         "sog": ("sog", "speed", "speedOverGround"),
         "cog": ("cog", "course", "courseOverGround"),
         "received_at": ("received_at", "timestamp", "time", "updated_at"),

backend/app/services/docs_gatekeeper.py

@@ -32,26 +32,31 @@ class DocsMetadata:
 
 DOCS_METADATA: tuple[DocsMetadata, ...] = (
     DocsMetadata(DOCS_README_FILENAME, DEFAULT_DOCS_SLUG, "public", "Overview", 0, "技术文档", "Technical Docs"),
-    DocsMetadata("quickstart.md", "quickstart", "public", "Manual", 1, "快速开始", "Quickstart"),
-    DocsMetadata("manual.md", "manual", "public", "Manual", 2, "Planet 使用手册", "Planet Manual"),
-    DocsMetadata("location-pipeline-user.md", "location-pipeline-user", "public", "Manual", 3, "Earth 位置候选采集使用手册", "Earth Location Candidate Collection User Guide"),
-    DocsMetadata("earth-frontend-context.md", "earth-frontend-context", "docs_developer", "Earth", 10, "Earth 前端结构", "Earth Frontend Context"),
-    DocsMetadata("earth-layer-style-reference.md", "earth-layer-style-reference", "docs_developer", "Earth", 11, "Earth 图层样式属性索引", "Earth Layer Style Reference"),
-    DocsMetadata("earth-render-layer-order.md", "earth-render-layer-order", "docs_developer", "Earth", 12, "Earth 渲染图层顺序", "Earth Render Layer Order"),
-    DocsMetadata("earth-satellite-footprint-policy.md", "earth-satellite-footprint-policy", "docs_developer", "Earth", 13, "Earth 卫星覆盖策略", "Earth Satellite Footprint Policy"),
+    DocsMetadata("manual.md", "manual", "public", "Manual", 1, "智能星球使用手册", "Intelligent Planet Manual"),
+    DocsMetadata("quickstart.md", "quickstart", "public", "Manual", 2, "快速开始", "Quickstart"),
+    DocsMetadata("faq.md", "faq", "public", "Manual", 3, "常见问题", "FAQ"),
+    DocsMetadata("platform-data-flows.md", "platform-data-flows", "docs_developer", "Architecture", 5, "业务架构与数据流转", "Business Architecture and Data Flows"),
+    DocsMetadata("naming-glossary.md", "naming-glossary", "docs_developer", "Architecture", 6, "命名与术语对照", "Naming Glossary"),
+    DocsMetadata("earth-frontend-context.md", "earth-frontend-context", "docs_developer", "Earth", 10, "智能星球前端结构", "Intelligent Planet Frontend Context"),
+    DocsMetadata("earth-layer-style-reference.md", "earth-layer-style-reference", "docs_developer", "Earth", 11, "智能星球图层样式属性索引", "Intelligent Planet Layer Style Reference"),
+    DocsMetadata("earth-render-layer-order.md", "earth-render-layer-order", "docs_developer", "Earth", 12, "智能星球渲染图层顺序", "Intelligent Planet Render Layer Order"),
+    DocsMetadata("earth-satellite-footprint-policy.md", "earth-satellite-footprint-policy", "docs_developer", "Earth", 13, "智能星球卫星覆盖策略", "Intelligent Planet Satellite Footprint Policy"),
     DocsMetadata("earth-bgp-context.md", "earth-bgp-context", "docs_developer", "Earth", 14, "BGP 态势上下文", "BGP Context"),
-    DocsMetadata("earth-news-live-streams-collector-format.md", "earth-news-live-streams-collector-format", "docs_developer", "Earth", 15, "新闻直播采集格式", "News Live Streams Collector Format"),
-    DocsMetadata("earth-interactable-usage.md", "earth-interactable-usage", "docs_developer", "Earth", 16, "Earth 可交互图标接入", "Earth Interactable Usage"),
-    DocsMetadata("earth-toolbar-overlay-coordination.md", "earth-toolbar-overlay-coordination", "docs_developer", "Earth", 17, "Earth 工具栏与浮层协同", "Earth Toolbar and Overlay Coordination"),
+    DocsMetadata("earth-interactable-usage.md", "earth-interactable-usage", "docs_developer", "Earth", 16, "智能星球可交互图标接入", "Intelligent Planet Interactable Usage"),
+    DocsMetadata("earth-toolbar-overlay-coordination.md", "earth-toolbar-overlay-coordination", "docs_developer", "Earth", 17, "智能星球工具栏与浮层协同", "Intelligent Planet Toolbar and Overlay Coordination"),
     DocsMetadata("frontend-admin-frontend-context.md", "frontend-admin-frontend-context", "docs_developer", "Frontend", 20, "控制台前端结构", "Admin Frontend Context"),
     DocsMetadata("frontend-layout-guidelines.md", "frontend-layout-guidelines", "docs_developer", "Frontend", 21, "前端布局指南", "Frontend Layout Guidelines"),
-    DocsMetadata("docs-gatekeeper-development.md", "docs-gatekeeper-development", "docs_developer", "Frontend", 22, "Docs Gatekeeper 开发说明", "Docs Gatekeeper Development Guide"),
+    DocsMetadata("tactile-ui-components.md", "tactile-ui-components", "docs_developer", "Frontend", 24, "Tactile UI 组件库", "Tactile UI Components"),
     DocsMetadata("backend-collectors.md", "backend-collectors", "docs_developer", "Backend", 30, "数据采集系统", "Data Collectors"),
     DocsMetadata("backend-system-service-control.md", "backend-system-service-control", "docs_admin", "Backend", 31, "系统服务控制", "System Service Control"),
     DocsMetadata("datasource-collector-settings-connectivity.md", "datasource-collector-settings-connectivity", "docs_developer", "Backend", 32, "数据源、采集器设置与连接验证", "Datasource Collector Settings and Connectivity"),
     DocsMetadata("backend-datasources-api-performance.md", "backend-datasources-api-performance", "docs_developer", "Backend", 33, "数据源 API 性能", "Datasource API Performance"),
-    DocsMetadata("location-pipeline-development.md", "location-pipeline-development", "docs_developer", "Backend", 34, "通用位置估算管线开发说明", "Shared Location Resolution Pipeline Development Guide"),
+    DocsMetadata("data-job-earth-sync-architecture.md", "data-job-earth-sync-architecture", "docs_developer", "Backend", 34, "数据作业与 Outbox 技术架构", "Data Jobs and Outbox Architecture"),
+    DocsMetadata("location-pipeline-development.md", "location-pipeline-development", "docs_developer", "Backend", 35, "通用位置估算管线开发说明", "Shared Location Resolution Pipeline Development Guide"),
+    DocsMetadata("earth-news-live-streams-collector-format.md", "earth-news-live-streams-collector-format", "docs_developer", "Backend", 36, "新闻直播采集格式", "News Live Streams Collector Format"),
+    DocsMetadata("docs-gatekeeper-development.md", "docs-gatekeeper-development", "docs_developer", "Backend", 37, "Docs Gatekeeper 开发说明", "Docs Gatekeeper Development Guide"),
     DocsMetadata("agents-aiprovider.md", "agents-aiprovider", "docs_developer", "Agents", 40, "AI Provider 指南", "AI Provider Guide"),
+    DocsMetadata("ops-runbook.md", "ops-runbook", "docs_admin", "Ops", 49, "智能星球运维手册", "Intelligent Planet Ops Runbook"),
     DocsMetadata("ops-docker-compose-buildx-upgrade.md", "ops-docker-compose-buildx-upgrade", "docs_admin", "Ops", 50, "Docker + Compose + Buildx 升级", "Docker + Compose + Buildx Upgrade"),
     DocsMetadata("ops-planet-sh-startup.md", "ops-planet-sh-startup", "docs_admin", "Ops", 51, "planet.sh 启动机制", "planet.sh Startup"),
 )

backend/app/services/earth_boundaries.py

@@ -0,0 +1,671 @@
+"""Earth boundary static asset service."""
+
+from __future__ import annotations
+
+import asyncio
+import hashlib
+import json
+import shutil
+import sys
+from datetime import UTC, datetime
+from pathlib import Path
+from typing import Any
+from uuid import uuid4
+
+import httpx
+
+
+REPO_ROOT = Path(__file__).resolve().parents[3]
+SOURCE_OUTPUT_DIR = REPO_ROOT / "data/earth-boundary-sources"
+SOURCE_MANIFEST_PATH = SOURCE_OUTPUT_DIR / "manifest.json"
+BUILD_RESULT_PATH = SOURCE_OUTPUT_DIR / "build-result.json"
+BUILD_JOB_PATH = SOURCE_OUTPUT_DIR / "build-job.json"
+BOUNDARY_OUTPUT_DIR = REPO_ROOT / "frontend/public/earth/data/boundaries/v1"
+BOUNDARY_MANIFEST_PATH = BOUNDARY_OUTPUT_DIR / "manifest.json"
+PMTILES_ARTIFACT_PATH = (
+    REPO_ROOT / "frontend/public/earth/data/boundaries/earth-boundaries-china-pov-v1.pmtiles"
+)
+LEGACY_GEOJSON_PATH = REPO_ROOT / "frontend/public/earth/data/countries-admin0.min.geojson"
+POV_POLICY_PATH = REPO_ROOT / "config/earth-boundary-pov-policy.china-v1.json"
+LOCAL_CONFIG_PATH = REPO_ROOT / "config/earth-boundary-sources.local.json"
+EXAMPLE_CONFIG_PATH = REPO_ROOT / "config/earth-boundary-sources.example.json"
+
+BOUNDARY_SOURCE_KINDS = {
+    "earth_admin0_boundaries": "admin0-boundaries",
+    "earth_coastline": "coastline",
+    "earth_claim_lines": "claim-lines",
+}
+
+DEFAULT_PUBLIC_BOUNDARY_SOURCES = {
+    "earth_admin0_boundaries": {
+        "displayName": "Natural Earth Admin-0 Countries",
+        "sourceKind": "admin0-boundaries",
+        "endpoint": "https://raw.githubusercontent.com/nvkelso/natural-earth-vector/master/geojson/ne_10m_admin_0_countries.geojson",
+        "method": "GET",
+        "headers": {},
+        "auth_type": "none",
+        "license": "Natural Earth public domain",
+    },
+    "earth_coastline": {
+        "displayName": "Natural Earth Coastline",
+        "sourceKind": "coastline",
+        "endpoint": "https://raw.githubusercontent.com/nvkelso/natural-earth-vector/master/geojson/ne_10m_coastline.geojson",
+        "method": "GET",
+        "headers": {},
+        "auth_type": "none",
+        "license": "Natural Earth public domain",
+    },
+    "earth_claim_lines": {
+        "displayName": "Natural Earth Disputed Boundaries",
+        "sourceKind": "claim-lines",
+        "endpoint": "https://raw.githubusercontent.com/nvkelso/natural-earth-vector/master/geojson/ne_10m_admin_0_boundary_lines_disputed_areas.geojson",
+        "method": "GET",
+        "headers": {},
+        "auth_type": "none",
+        "license": "Natural Earth public domain",
+    },
+}
+
+BUILD_CONFIG = {
+    "builder": "scripts/build_earth_boundary_pmtiles.py",
+    "format": "pmtiles+mvt",
+    "production_target": "pmtiles-mvt",
+}
+
+
+class EarthBoundaryBuildError(RuntimeError):
+    def __init__(self, message: str, *, code: str = "build_failed", details: Any = None) -> None:
+        super().__init__(message)
+        self.code = code
+        self.details = details
+
+
+_build_job_lock = asyncio.Lock()
+_build_task: asyncio.Task | None = None
+_build_job_state: dict[str, Any] = {}
+
+
+def _utc_now_iso() -> str:
+    return datetime.now(UTC).isoformat()
+
+
+def _public_job_state() -> dict[str, Any]:
+    if _build_job_state:
+        return dict(_build_job_state)
+    return _read_json(BUILD_JOB_PATH)
+
+
+def get_boundary_build_status() -> dict[str, Any]:
+    return {"job": _public_job_state()}
+
+
+def _set_job_state(**updates: Any) -> dict[str, Any]:
+    global _build_job_state
+    current = dict(_build_job_state)
+    current.update(updates)
+    current["updated_at"] = _utc_now_iso()
+    _build_job_state = current
+    _write_json(BUILD_JOB_PATH, current)
+    return current
+
+
+def _append_job_log(message: str) -> None:
+    logs = list(_build_job_state.get("logs") or [])
+    logs.append({"time": _utc_now_iso(), "message": message})
+    _set_job_state(logs=logs[-40:])
+
+
+def _update_job_progress(progress: float, phase: str, message: str, **extra: Any) -> None:
+    bounded_progress = max(0, min(100, int(round(progress))))
+    _set_job_state(
+        status="running",
+        progress=bounded_progress,
+        phase=phase,
+        message=message,
+        **extra,
+    )
+
+
+def _read_json(path: Path) -> dict[str, Any]:
+    if not path.exists():
+        return {}
+    with path.open("r", encoding="utf-8") as f:
+        payload = json.load(f)
+    return payload if isinstance(payload, dict) else {}
+
+
+def _write_json(path: Path, payload: dict[str, Any]) -> None:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with path.open("w", encoding="utf-8") as f:
+        json.dump(payload, f, ensure_ascii=False, indent=2)
+        f.write("\n")
+
+
+def _sha256_bytes(payload: bytes) -> str:
+    return hashlib.sha256(payload).hexdigest()
+
+
+def _stable_json_hash(payload: Any) -> str:
+    encoded = json.dumps(payload, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
+    return hashlib.sha256(encoded.encode("utf-8")).hexdigest()
+
+
+def _artifact_extension(endpoint: str, content_type: str, payload: bytes) -> str:
+    suffix = Path(endpoint.split("?", 1)[0]).suffix.lower()
+    if suffix in {".json", ".geojson", ".zip", ".pbf"}:
+        return suffix
+    if "geo+json" in content_type or b'"FeatureCollection"' in payload[:4096]:
+        return ".geojson"
+    if "json" in content_type:
+        return ".json"
+    return ".dat"
+
+
+def _json_feature_count(payload: Any) -> int:
+    if isinstance(payload, dict) and isinstance(payload.get("features"), list):
+        return len(payload["features"])
+    if isinstance(payload, list):
+        return len(payload)
+    return 1 if payload else 0
+
+
+def _directory_stats(path: Path) -> dict[str, int]:
+    if not path.exists():
+        return {"file_count": 0, "size_bytes": 0}
+    files = [item for item in path.rglob("*") if item.is_file()]
+    return {"file_count": len(files), "size_bytes": sum(item.stat().st_size for item in files)}
+
+
+def _load_source_feature_collection(source: dict[str, Any]) -> dict[str, Any]:
+    path = REPO_ROOT / source["path"]
+    payload = _read_json(path)
+    features = payload.get("features") if isinstance(payload, dict) else None
+    return {
+        "type": "FeatureCollection",
+        "features": features if isinstance(features, list) else [],
+    }
+
+
+def _write_high_precision_geojson_manifest(
+    sources: list[dict[str, Any]],
+    build_input_hash: str,
+    missing_tools: list[str],
+) -> dict[str, Any]:
+    BOUNDARY_OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
+    admin0 = next(source for source in sources if source["kind"] == "admin0-boundaries")
+    coastline = next(source for source in sources if source["kind"] == "coastline")
+    claim_lines = next(source for source in sources if source["kind"] == "claim-lines")
+
+    admin0_payload = _load_source_feature_collection(admin0)
+    coastline_payload = _load_source_feature_collection(coastline)
+    claim_payload = _load_source_feature_collection(claim_lines)
+    for feature in coastline_payload["features"]:
+        props = feature.setdefault("properties", {})
+        if isinstance(props, dict):
+            props["PLANET_LAYER"] = "coastline"
+
+    base_payload = {
+        "type": "FeatureCollection",
+        "features": [*admin0_payload["features"], *coastline_payload["features"]],
+    }
+    base_path = BOUNDARY_OUTPUT_DIR / "earth-boundaries-high-precision-base.geojson"
+    hover_path = BOUNDARY_OUTPUT_DIR / "earth-boundaries-high-precision-hover.geojson"
+    claim_path = BOUNDARY_OUTPUT_DIR / "earth-boundaries-high-precision-claims.geojson"
+    _write_json(base_path, base_payload)
+    _write_json(hover_path, admin0_payload)
+    _write_json(claim_path, claim_payload)
+
+    manifest = {
+        "version": "natural-earth-v1",
+        "builtAt": _utc_now_iso(),
+        "tileProvider": "geojson-high-precision",
+        "format": "geojson-directory",
+        "buildInputHash": build_input_hash,
+        "base": base_path.name,
+        "hoverIndex": hover_path.name,
+        "claimLine": claim_path.name,
+        "sourceFeatureCount": {
+            "admin0": len(admin0_payload["features"]),
+            "coastline": len(coastline_payload["features"]),
+            "claimLines": len(claim_payload["features"]),
+        },
+        "pmtiles": None,
+        "missingTools": missing_tools,
+    }
+    _write_json(BOUNDARY_MANIFEST_PATH, manifest)
+    return manifest
+
+
+def _relative(path: Path) -> str:
+    return str(path.relative_to(REPO_ROOT))
+
+
+def load_boundary_config() -> tuple[dict[str, Any], str]:
+    if LOCAL_CONFIG_PATH.exists():
+        return _read_json(LOCAL_CONFIG_PATH), "local"
+    return _read_json(EXAMPLE_CONFIG_PATH), "example"
+
+
+def save_boundary_config(payload: dict[str, Any]) -> dict[str, Any]:
+    if not isinstance(payload, dict):
+        raise EarthBoundaryBuildError("Earth boundary config must be a JSON object", code="invalid_config")
+    _write_json(LOCAL_CONFIG_PATH, payload)
+    return get_boundary_status()
+
+
+def _source_configs(payload: dict[str, Any]) -> dict[str, Any]:
+    raw_sources = payload.get("collectorConfigs") or payload.get("sources") or {}
+    return raw_sources if isinstance(raw_sources, dict) else {}
+
+
+def _is_placeholder_endpoint(endpoint: Any) -> bool:
+    value = str(endpoint or "").strip()
+    return not value or "example.com" in value
+
+
+def _source_configs_with_defaults(payload: dict[str, Any]) -> dict[str, Any]:
+    raw_sources = _source_configs(payload)
+    merged: dict[str, Any] = {}
+    for source_key, default_config in DEFAULT_PUBLIC_BOUNDARY_SOURCES.items():
+        configured = raw_sources.get(source_key)
+        if not isinstance(configured, dict) or _is_placeholder_endpoint(configured.get("endpoint")):
+            merged[source_key] = dict(default_config)
+        else:
+            merged[source_key] = {**default_config, **configured}
+    for source_key, source_config in raw_sources.items():
+        if source_key not in merged:
+            merged[source_key] = source_config
+    return merged
+
+
+def _build_input_hash(source_manifest: dict[str, Any]) -> str:
+    return _stable_json_hash(
+        {
+            "source_manifest_schema": source_manifest.get("schema"),
+            "sources": [
+                {
+                    "id": source.get("id"),
+                    "sha256": source.get("sha256"),
+                    "kind": source.get("kind"),
+                }
+                for source in source_manifest.get("sources", [])
+            ],
+            "pov_policy": source_manifest.get("povPolicy"),
+            "build_config": BUILD_CONFIG,
+        }
+    )
+
+
+def _has_current_artifacts(boundary_manifest: dict[str, Any], build_input_hash: str) -> bool:
+    return (
+        bool(boundary_manifest)
+        and boundary_manifest.get("buildInputHash") == build_input_hash
+        and boundary_manifest.get("tileProvider") == "pmtiles-mvt"
+        and PMTILES_ARTIFACT_PATH.exists()
+    )
+
+
+def get_boundary_status() -> dict[str, Any]:
+    config_payload, config_source = load_boundary_config()
+    effective_source_configs = _source_configs_with_defaults(config_payload)
+    boundary_manifest = _read_json(BOUNDARY_MANIFEST_PATH)
+    pmtiles_exists = PMTILES_ARTIFACT_PATH.exists()
+    manifest_exists = BOUNDARY_MANIFEST_PATH.exists()
+    high_precision_ready = (
+        manifest_exists
+        and (
+            (
+                boundary_manifest.get("tileProvider") == "pmtiles-mvt"
+                and pmtiles_exists
+            )
+            or boundary_manifest.get("tileProvider") == "geojson-high-precision"
+        )
+    )
+    legacy_exists = LEGACY_GEOJSON_PATH.exists()
+    provider = (
+        boundary_manifest.get("tileProvider")
+        if high_precision_ready
+        else "legacy-geojson" if legacy_exists else "missing"
+    )
+    return {
+        "provider": provider,
+        "high_precision_ready": high_precision_ready,
+        "fallback_available": legacy_exists,
+        "config_source": config_source,
+        "config_path": _relative(LOCAL_CONFIG_PATH),
+        "config_exists": LOCAL_CONFIG_PATH.exists(),
+        "config": config_payload,
+        "effective_default_sources": [
+            source_key
+            for source_key, source_config in effective_source_configs.items()
+            if source_key in DEFAULT_PUBLIC_BOUNDARY_SOURCES
+            and source_config.get("endpoint") == DEFAULT_PUBLIC_BOUNDARY_SOURCES[source_key]["endpoint"]
+        ],
+        "manifest": {
+            "path": _relative(BOUNDARY_MANIFEST_PATH),
+            "exists": manifest_exists,
+            "tileProvider": boundary_manifest.get("tileProvider"),
+            "buildInputHash": boundary_manifest.get("buildInputHash"),
+            "builtAt": boundary_manifest.get("builtAt"),
+        },
+        "pmtiles": {
+            "path": _relative(PMTILES_ARTIFACT_PATH),
+            "exists": pmtiles_exists,
+            "size_bytes": PMTILES_ARTIFACT_PATH.stat().st_size if pmtiles_exists else 0,
+        },
+        "legacy": {
+            "path": _relative(LEGACY_GEOJSON_PATH),
+            "exists": legacy_exists,
+            "size_bytes": LEGACY_GEOJSON_PATH.stat().st_size if legacy_exists else 0,
+        },
+        "source_manifest": {
+            "path": _relative(SOURCE_MANIFEST_PATH),
+            "exists": SOURCE_MANIFEST_PATH.exists(),
+        },
+        "last_build": _read_json(BUILD_RESULT_PATH),
+        "current_job": _public_job_state(),
+    }
+
+
+async def _download_source(
+    source_key: str,
+    source_config: dict[str, Any],
+    progress_callback: Any = None,
+) -> dict[str, Any]:
+    endpoint = str(source_config.get("endpoint") or "").strip()
+    if _is_placeholder_endpoint(endpoint):
+        raise EarthBoundaryBuildError(
+            f"{source_key} endpoint is not configured",
+            code="source_not_configured",
+            details={"source": source_key},
+        )
+    method = str(source_config.get("method") or "GET").upper()
+    if method not in {"GET", "POST"}:
+        raise EarthBoundaryBuildError(
+            f"{source_key} method must be GET or POST",
+            code="invalid_config",
+            details={"source": source_key, "method": method},
+        )
+
+    if endpoint.startswith("file://") or Path(endpoint).expanduser().exists():
+        payload = Path(endpoint.removeprefix("file://")).expanduser().read_bytes()
+        content_type = "application/octet-stream"
+        if progress_callback:
+            progress_callback(1, len(payload), len(payload))
+    else:
+        timeout = float(source_config.get("timeout") or 120)
+        headers = source_config.get("headers") if isinstance(source_config.get("headers"), dict) else {}
+        async with httpx.AsyncClient(timeout=timeout, follow_redirects=True) as client:
+            async with client.stream(method, endpoint, headers=headers) as response:
+                response.raise_for_status()
+                content_type = response.headers.get("content-type", "")
+                total = int(response.headers.get("content-length") or 0)
+                chunks = []
+                downloaded = 0
+                async for chunk in response.aiter_bytes():
+                    if not chunk:
+                        continue
+                    chunks.append(chunk)
+                    downloaded += len(chunk)
+                    if progress_callback:
+                        progress_callback(
+                            (downloaded / total) if total else None,
+                            downloaded,
+                            total,
+                        )
+                payload = b"".join(chunks)
+
+    extension = _artifact_extension(endpoint, content_type, payload)
+    parsed: Any = None
+    if extension in {".json", ".geojson"}:
+        parsed = json.loads(payload.decode("utf-8"))
+    feature_count = _json_feature_count(parsed)
+    if feature_count <= 0:
+        raise EarthBoundaryBuildError(
+            f"{source_key} downloaded payload contains no features",
+            code="empty_source",
+            details={"source": source_key},
+        )
+
+    sha256 = _sha256_bytes(payload)
+    source_dir = SOURCE_OUTPUT_DIR / source_key
+    source_dir.mkdir(parents=True, exist_ok=True)
+    artifact_path = source_dir / f"{sha256}{extension}"
+    artifact_path.write_bytes(payload)
+    return {
+        "id": source_key,
+        "kind": source_config.get("sourceKind") or BOUNDARY_SOURCE_KINDS[source_key],
+        "path": _relative(artifact_path),
+        "sha256": sha256,
+        "featureCount": feature_count,
+        "license": source_config.get("license"),
+    }
+
+
+async def _run_step(args: list[str]) -> dict[str, Any]:
+    process = await asyncio.create_subprocess_exec(
+        sys.executable,
+        *args,
+        cwd=REPO_ROOT,
+        stdout=asyncio.subprocess.PIPE,
+        stderr=asyncio.subprocess.PIPE,
+    )
+    stdout_bytes, stderr_bytes = await process.communicate()
+    stdout = stdout_bytes.decode("utf-8", errors="replace").strip()
+    stderr = stderr_bytes.decode("utf-8", errors="replace").strip()
+    payload: dict[str, Any] = {"stdout": stdout, "stderr": stderr, "returncode": process.returncode}
+    last_line = stdout.splitlines()[-1:] or []
+    if last_line:
+        try:
+            payload["result"] = json.loads(last_line[0])
+        except json.JSONDecodeError:
+            payload["result"] = last_line[0]
+    if process.returncode != 0:
+        raise EarthBoundaryBuildError(
+            stderr or stdout or f"command failed: {' '.join(args)}",
+            code="build_command_failed",
+            details=payload,
+        )
+    return payload
+
+
+async def build_boundary_assets(progress_callback: Any = None) -> dict[str, Any]:
+    config_payload, config_source = load_boundary_config()
+
+    source_configs = _source_configs_with_defaults(config_payload)
+    missing = [source for source in BOUNDARY_SOURCE_KINDS if source not in source_configs]
+    if missing:
+        raise EarthBoundaryBuildError(
+            f"Missing Earth boundary source configs: {', '.join(missing)}",
+            code="missing_sources",
+            details={"missing": missing},
+        )
+
+    sources = []
+    source_keys = list(BOUNDARY_SOURCE_KINDS)
+    for index, source_key in enumerate(source_keys):
+        source_config = source_configs[source_key]
+        if not isinstance(source_config, dict):
+            raise EarthBoundaryBuildError(
+                f"{source_key} config must be an object",
+                code="invalid_config",
+                details={"source": source_key},
+            )
+        source_start = 8 + index * 18
+        source_end = source_start + 18
+        if progress_callback:
+            progress_callback(source_start, "download", f"正在下载 {source_key}")
+
+        def report_download_progress(ratio: float | None, downloaded: int, total: int) -> None:
+            if not progress_callback:
+                return
+            if ratio is None:
+                progress_callback(source_start + 8, "download", f"{source_key} 已下载 {downloaded} bytes")
+                return
+            progress_callback(
+                source_start + (source_end - source_start) * ratio,
+                "download",
+                f"{source_key} 下载 {int(ratio * 100)}%",
+                downloaded_bytes=downloaded,
+                total_bytes=total,
+            )
+
+        sources.append(await _download_source(source_key, source_config, report_download_progress))
+
+    source_manifest = {
+        "schema": "planet-earth-boundary-sources/v2",
+        "sources": sources,
+        "povPolicy": _read_json(POV_POLICY_PATH),
+    }
+    if progress_callback:
+        progress_callback(65, "manifest", "正在写入边界源 manifest")
+    _write_json(SOURCE_MANIFEST_PATH, source_manifest)
+    build_input_hash = _build_input_hash(source_manifest)
+
+    boundary_manifest = _read_json(BOUNDARY_MANIFEST_PATH)
+    build_skipped = _has_current_artifacts(boundary_manifest, build_input_hash)
+    missing_tools = [tool for tool in ("tippecanoe", "pmtiles") if shutil.which(tool) is None]
+    if missing_tools and not build_skipped:
+        if progress_callback:
+            progress_callback(82, "build", "缺少 PMTiles 工具，正在生成 GeoJSON 高清包")
+        boundary_manifest = _write_high_precision_geojson_manifest(
+            sources,
+            build_input_hash,
+            missing_tools,
+        )
+        result = {
+            "status": "built_geojson_fallback",
+            "code": "missing_tools",
+            "missing_tools": missing_tools,
+            "sources": sources,
+            "boundary_manifest": _relative(BOUNDARY_MANIFEST_PATH),
+            "manifest": boundary_manifest,
+        }
+        _write_json(BUILD_RESULT_PATH, result)
+        if progress_callback:
+            progress_callback(96, "finalize", "GeoJSON 高清国界包已生成")
+        return {**get_boundary_status(), "build": result}
+
+    if build_skipped:
+        if progress_callback:
+            progress_callback(96, "unchanged", "高精国界已是最新")
+        build_result = {
+            "status": "unchanged",
+            "reason": "source manifest and build config hash unchanged",
+            "buildInputHash": build_input_hash,
+        }
+    else:
+        if progress_callback:
+            progress_callback(72, "build", "正在构建 PMTiles/MVT")
+        admin0 = next(source for source in sources if source["kind"] == "admin0-boundaries")
+        coastline = next(source for source in sources if source["kind"] == "coastline")
+        claim_lines = next(source for source in sources if source["kind"] == "claim-lines")
+        build_result = await _run_step(
+            [
+                "scripts/build_earth_boundary_pmtiles.py",
+                "--admin0-source",
+                admin0["path"],
+                "--coastline-source",
+                coastline["path"],
+                "--claims-source",
+                claim_lines["path"],
+                "--output",
+                _relative(PMTILES_ARTIFACT_PATH),
+                "--manifest",
+                _relative(BOUNDARY_MANIFEST_PATH),
+                "--build-input-hash",
+                build_input_hash,
+                "--pov-policy",
+                _relative(POV_POLICY_PATH),
+            ]
+        )
+        if progress_callback:
+            progress_callback(95, "finalize", "正在校验构建产物")
+
+    boundary_manifest = _read_json(BOUNDARY_MANIFEST_PATH)
+    boundary_stats = _directory_stats(BOUNDARY_OUTPUT_DIR)
+    result = {
+        "status": "unchanged" if build_skipped else "built",
+        "sources": sources,
+        "source_manifest": _relative(SOURCE_MANIFEST_PATH),
+        "boundary_manifest": _relative(BOUNDARY_MANIFEST_PATH),
+        "pmtiles_artifact": _relative(PMTILES_ARTIFACT_PATH),
+        "pmtiles_exists": PMTILES_ARTIFACT_PATH.exists(),
+        "boundary_stats": boundary_stats,
+        "manifest": boundary_manifest,
+        "build_result": build_result,
+    }
+    _write_json(BUILD_RESULT_PATH, result)
+    return {**get_boundary_status(), "build": result}
+
+
+async def _run_boundary_build_job(job_id: str) -> None:
+    def report(progress: float, phase: str, message: str, **extra: Any) -> None:
+        if _build_job_state.get("id") != job_id:
+            return
+        _update_job_progress(progress, phase, message, **extra)
+
+    try:
+        report(3, "prepare", "正在准备高精国界构建")
+        result = await build_boundary_assets(report)
+        _set_job_state(
+            id=job_id,
+            status="succeeded",
+            progress=100,
+            phase="complete",
+            message="高精国界构建完成",
+            finished_at=_utc_now_iso(),
+            result={
+                "provider": result.get("provider"),
+                "high_precision_ready": result.get("high_precision_ready"),
+                "pmtiles": result.get("pmtiles"),
+                "manifest": result.get("manifest"),
+            },
+        )
+        _append_job_log("高精国界构建完成")
+    except EarthBoundaryBuildError as exc:
+        _set_job_state(
+            id=job_id,
+            status="failed",
+            progress=_build_job_state.get("progress", 0),
+            phase="failed",
+            message=str(exc),
+            code=exc.code,
+            details=exc.details,
+            finished_at=_utc_now_iso(),
+        )
+        _append_job_log(str(exc))
+    except Exception as exc:  # pragma: no cover - defensive guard for background task
+        _set_job_state(
+            id=job_id,
+            status="failed",
+            progress=_build_job_state.get("progress", 0),
+            phase="failed",
+            message=str(exc),
+            code="build_failed",
+            finished_at=_utc_now_iso(),
+        )
+        _append_job_log(str(exc))
+
+
+async def start_boundary_build_job() -> dict[str, Any]:
+    global _build_task
+    async with _build_job_lock:
+        if _build_task and not _build_task.done():
+            return {"accepted": False, "job": _public_job_state()}
+        job_id = uuid4().hex
+        _set_job_state(
+            id=job_id,
+            status="queued",
+            progress=0,
+            phase="queued",
+            message="高精国界构建已加入队列",
+            logs=[],
+            started_at=_utc_now_iso(),
+            finished_at=None,
+            code=None,
+            details=None,
+        )
+        _append_job_log("高精国界构建已启动")
+        _build_task = asyncio.create_task(_run_boundary_build_job(job_id))
+        return {"accepted": True, "job": _public_job_state()}

backend/app/services/earth_db_change_listener.py

@@ -0,0 +1,482 @@
+"""PostgreSQL LISTEN/NOTIFY bridge for Earth layer refresh events."""
+
+from __future__ import annotations
+
+import asyncio
+import json
+from collections import deque
+from dataclasses import dataclass, field
+from datetime import UTC, datetime
+from time import monotonic
+from typing import Any, Awaitable, Callable
+
+import asyncpg
+
+from app.core.config import settings
+from app.core.logging import get_logger
+from app.core.time import to_iso8601_utc
+from app.core.websocket.broadcaster import broadcaster
+from app.services.earth_layer_adapters import (
+    get_earth_refresh_strategy_for_change,
+    get_earth_update_layers_for_change,
+    get_earth_update_layers_for_source,
+)
+from app.services.earth_layer_cache import invalidate_earth_layer_cache_for_source
+
+logger = get_logger(__name__)
+
+EARTH_DATA_CHANGES_CHANNEL = "planet_earth_data_changes"
+DEFAULT_DEBOUNCE_SECONDS = 0.25
+DEFAULT_MAX_WAIT_SECONDS = 1.5
+DELETE_FAST_FLUSH_SECONDS = 0.05
+LISTEN_KEEPALIVE_SECONDS = 5.0
+OUTBOX_POLL_LIMIT = 5000
+MAX_ENTITY_KEY_SAMPLES = 20
+MAX_SEEN_EVENT_IDS = 20000
+
+BroadcastFn = Callable[[dict[str, Any]], Awaitable[None]]
+InvalidateFn = Callable[[str], int]
+
+
+def normalize_asyncpg_dsn(dsn: str) -> str:
+    """Convert SQLAlchemy asyncpg URLs into asyncpg-compatible URLs."""
+    return dsn.replace("postgresql+asyncpg://", "postgresql://", 1)
+
+
+def build_earth_update_from_db_payload(payload: dict[str, Any]) -> dict[str, Any] | None:
+    table = payload.get("table")
+    source = str(payload.get("source") or "").strip()
+    table_name = str(table or "").strip()
+    if not source and not table_name:
+        return None
+    layers = get_earth_update_layers_for_change(table_name, source)
+    if not layers:
+        return None
+    refresh_strategy = get_earth_refresh_strategy_for_change(table_name, source) or "clear_then_reload"
+    source_has_adapter = bool(get_earth_update_layers_for_source(source))
+    effective_source = source if source_has_adapter else (table_name if table_name else source)
+    operation = payload.get("operation")
+    update: dict[str, Any] = {
+        "event": "earth.layer.changed",
+        "action": "database_changed",
+        "source": effective_source,
+        "original_source": source or None,
+        "table": table_name or None,
+        "data_type": effective_source,
+        "layers": layers,
+        "refresh_strategy": refresh_strategy,
+        "operation": operation,
+        "entity_key": payload.get("entity_key"),
+        "timestamp": to_iso8601_utc(datetime.now(UTC)),
+    }
+    if table_name == "earth_interactables" and refresh_strategy == "delta":
+        ids = payload.get("entity_keys")
+        if not isinstance(ids, list):
+            ids = [payload.get("entity_key")] if payload.get("entity_key") else []
+        update.update(
+            {
+                "entity": "interactable",
+                "action": "deleted" if operation == "DELETE" else "changed",
+                "ids": [str(item) for item in ids if item],
+                "item": None,
+            }
+        )
+    return {
+        **update,
+    }
+
+
+@dataclass
+class PendingEarthDbChange:
+    source: str
+    layers: list[str]
+    table: str | None = None
+    refresh_strategy: str = "clear_then_reload"
+    entity: str | None = None
+    action: str = "database_changed"
+    records_processed: int = 0
+    operations: set[str] = field(default_factory=set)
+    entity_keys: list[str] = field(default_factory=list)
+    first_occurred_at: str | None = None
+    last_occurred_at: str | None = None
+    first_seen_monotonic: float = field(default_factory=monotonic)
+    last_seen_monotonic: float = field(default_factory=monotonic)
+
+    def add(self, payload: dict[str, Any]) -> None:
+        self.last_seen_monotonic = monotonic()
+        records_processed = payload.get("records_processed", 1)
+        try:
+            records_processed = int(records_processed)
+        except (TypeError, ValueError):
+            records_processed = 1
+        self.records_processed += max(records_processed, 1)
+        operation = payload.get("operation")
+        if operation:
+            self.operations.add(str(operation))
+        entity_keys = payload.get("entity_keys")
+        if not isinstance(entity_keys, list):
+            entity_key = payload.get("entity_key")
+            entity_keys = [entity_key] if entity_key else []
+        for entity_key in entity_keys:
+            if entity_key and len(self.entity_keys) < MAX_ENTITY_KEY_SAMPLES:
+                self.entity_keys.append(str(entity_key))
+        occurred_at = payload.get("occurred_at")
+        if occurred_at:
+            occurred_at = str(occurred_at)
+            self.first_occurred_at = self.first_occurred_at or occurred_at
+            self.last_occurred_at = occurred_at
+
+
+class EarthDbChangeDispatcher:
+    """Debounces database notifications and broadcasts Earth refresh hints."""
+
+    def __init__(
+        self,
+        *,
+        broadcast_earth_update: BroadcastFn | None = None,
+        invalidate_cache: InvalidateFn | None = None,
+        debounce_seconds: float = DEFAULT_DEBOUNCE_SECONDS,
+        max_wait_seconds: float = DEFAULT_MAX_WAIT_SECONDS,
+    ) -> None:
+        self._broadcast_earth_update = broadcast_earth_update or broadcaster.broadcast_earth_update
+        self._invalidate_cache = invalidate_cache or invalidate_earth_layer_cache_for_source
+        self._debounce_seconds = debounce_seconds
+        self._max_wait_seconds = max(max_wait_seconds, debounce_seconds)
+        self._pending: dict[str, PendingEarthDbChange] = {}
+        self._flush_tasks: dict[str, asyncio.Task[None]] = {}
+        self._seen_event_ids: set[int] = set()
+        self._seen_event_order: deque[int] = deque()
+
+    def handle_notification(self, payload_text: str) -> bool:
+        try:
+            payload = json.loads(payload_text)
+        except json.JSONDecodeError:
+            logger.warning_event(
+                "Ignoring malformed Earth database change notification",
+                event="earth.db_changes.notification_malformed",
+            )
+            return False
+        if not isinstance(payload, dict):
+            return False
+        return self.handle_payload(payload)
+
+    def handle_payload(self, payload: dict[str, Any]) -> bool:
+        event_id = payload.get("event_id")
+        if event_id is not None:
+            try:
+                normalized_event_id = int(event_id)
+            except (TypeError, ValueError):
+                normalized_event_id = None
+            if normalized_event_id is not None:
+                if normalized_event_id in self._seen_event_ids:
+                    return False
+                self._remember_event_id(normalized_event_id)
+
+        update = build_earth_update_from_db_payload(payload)
+        if not update:
+            return False
+
+        source = update["source"]
+        pending = self._pending.get(source)
+        if pending is None:
+            pending = PendingEarthDbChange(
+                source=source,
+                layers=list(update["layers"]),
+                table=update.get("table"),
+                refresh_strategy=str(update.get("refresh_strategy") or "clear_then_reload"),
+                entity=update.get("entity"),
+                action=str(update.get("action") or "database_changed"),
+            )
+            self._pending[source] = pending
+        pending.add(payload)
+
+        task = self._flush_tasks.pop(source, None)
+        if task and not task.done():
+            task.cancel()
+        self._flush_tasks[source] = asyncio.create_task(
+            self._flush_later(source, delay_seconds=self._next_flush_delay(pending))
+        )
+        return True
+
+    def _next_flush_delay(self, pending: PendingEarthDbChange) -> float:
+        if "DELETE" in pending.operations and pending.refresh_strategy == "clear_then_reload":
+            return DELETE_FAST_FLUSH_SECONDS
+        elapsed = max(0.0, monotonic() - pending.first_seen_monotonic)
+        remaining = self._max_wait_seconds - elapsed
+        if remaining <= 0:
+            return 0.0
+        return min(self._debounce_seconds, remaining)
+
+    def _remember_event_id(self, event_id: int) -> None:
+        self._seen_event_ids.add(event_id)
+        self._seen_event_order.append(event_id)
+        while len(self._seen_event_order) > MAX_SEEN_EVENT_IDS:
+            expired_event_id = self._seen_event_order.popleft()
+            self._seen_event_ids.discard(expired_event_id)
+
+    async def _flush_later(self, source: str, *, delay_seconds: float) -> None:
+        try:
+            if delay_seconds > 0:
+                await asyncio.sleep(delay_seconds)
+            await self.flush_source(source)
+        except asyncio.CancelledError:
+            raise
+        except Exception as exc:
+            logger.exception_event(
+                "Failed to broadcast debounced Earth database change",
+                event="earth.db_changes.flush_failed",
+                context={"source": source, "error": str(exc)},
+            )
+        finally:
+            current = self._flush_tasks.get(source)
+            if current is asyncio.current_task():
+                self._flush_tasks.pop(source, None)
+
+    async def flush_source(self, source: str) -> None:
+        pending = self._pending.get(source)
+        if pending is None:
+            return
+
+        flushed_at = datetime.now(UTC)
+        deleted_cache_entries = self._invalidate_cache(source)
+        operations = sorted(pending.operations)
+        payload: dict[str, Any] = {
+            "event": "earth.layer.changed",
+            "action": "database_changed",
+            "source": source,
+            "table": pending.table,
+            "data_type": source,
+            "layers": pending.layers,
+            "refresh_strategy": pending.refresh_strategy,
+            "records_processed": pending.records_processed,
+            "operations": operations,
+            "operation": operations[-1] if len(operations) == 1 else None,
+            "entity_keys": pending.entity_keys,
+            "entity_key_sample_size": len(pending.entity_keys),
+            "cache_entries_invalidated": deleted_cache_entries,
+            "first_occurred_at": pending.first_occurred_at,
+            "last_occurred_at": pending.last_occurred_at,
+            "debounce_ms": int((monotonic() - pending.first_seen_monotonic) * 1000),
+            "total_latency_ms": self._total_latency_ms(pending, flushed_at),
+            "timestamp": to_iso8601_utc(flushed_at),
+        }
+        if pending.entity == "interactable":
+            payload.update(
+                {
+                    "entity": "interactable",
+                    "action": "deleted" if "DELETE" in pending.operations else "changed",
+                    "ids": pending.entity_keys,
+                    "item": None,
+                }
+            )
+        await self._broadcast_earth_update(payload)
+        self._pending.pop(source, None)
+        logger.info_event(
+            "Broadcasted Earth database change",
+            event="earth.db_changes.broadcasted",
+            context={
+                "source": source,
+                "layers": pending.layers,
+                "records_processed": pending.records_processed,
+                "cache_entries_invalidated": deleted_cache_entries,
+                "debounce_ms": int((monotonic() - pending.first_seen_monotonic) * 1000),
+                "total_latency_ms": payload["total_latency_ms"],
+            },
+        )
+
+    @staticmethod
+    def _total_latency_ms(pending: PendingEarthDbChange, flushed_at: datetime) -> int | None:
+        occurred_at = pending.first_occurred_at
+        if not occurred_at:
+            return None
+        try:
+            normalized = occurred_at.replace("Z", "+00:00")
+            occurred = datetime.fromisoformat(normalized)
+            if occurred.tzinfo is None:
+                occurred = occurred.replace(tzinfo=UTC)
+            return max(0, int((flushed_at - occurred.astimezone(UTC)).total_seconds() * 1000))
+        except ValueError:
+            return None
+
+    async def flush_all(self) -> None:
+        sources = list(self._pending)
+        for source in sources:
+            task = self._flush_tasks.pop(source, None)
+            if task and not task.done():
+                task.cancel()
+            await self.flush_source(source)
+
+    async def stop(self) -> None:
+        tasks = [task for task in self._flush_tasks.values() if not task.done()]
+        for task in tasks:
+            task.cancel()
+        if tasks:
+            await asyncio.gather(*tasks, return_exceptions=True)
+        self._flush_tasks.clear()
+        await self.flush_all()
+
+
+class EarthDbChangeListener:
+    def __init__(
+        self,
+        *,
+        dsn: str,
+        dispatcher: EarthDbChangeDispatcher,
+        channel: str = EARTH_DATA_CHANGES_CHANNEL,
+    ) -> None:
+        self._dsn = normalize_asyncpg_dsn(dsn)
+        self._dispatcher = dispatcher
+        self._channel = channel
+        self._task: asyncio.Task[None] | None = None
+        self._stop_event: asyncio.Event | None = None
+        self._connection: asyncpg.Connection | None = None
+        self._loop: asyncio.AbstractEventLoop | None = None
+
+    def start(self) -> None:
+        if self._task and not self._task.done():
+            return
+        self._loop = asyncio.get_running_loop()
+        self._stop_event = asyncio.Event()
+        self._task = asyncio.create_task(self._run())
+
+    async def stop(self) -> None:
+        if self._stop_event:
+            self._stop_event.set()
+        if self._connection:
+            await self._connection.close()
+        if self._task:
+            await asyncio.gather(self._task, return_exceptions=True)
+        await self._dispatcher.stop()
+
+    async def _run(self) -> None:
+        backoff_seconds = 1.0
+        assert self._stop_event is not None
+
+        while not self._stop_event.is_set():
+            try:
+                self._connection = await asyncpg.connect(self._dsn)
+                await self._connection.add_listener(self._channel, self._on_notification)
+                logger.info_event(
+                    "Earth database change listener connected",
+                    event="earth.db_changes.connected",
+                    context={"channel": self._channel},
+                )
+                backoff_seconds = 1.0
+                while not self._stop_event.is_set():
+                    try:
+                        await asyncio.wait_for(
+                            self._stop_event.wait(),
+                            timeout=LISTEN_KEEPALIVE_SECONDS,
+                        )
+                    except asyncio.TimeoutError:
+                        await self._poll_outbox()
+            except asyncio.CancelledError:
+                raise
+            except Exception as exc:
+                logger.exception_event(
+                    "Earth database change listener failed",
+                    event="earth.db_changes.listener_failed",
+                    context={"channel": self._channel, "error": str(exc)},
+                )
+                try:
+                    await asyncio.wait_for(self._stop_event.wait(), timeout=backoff_seconds)
+                except asyncio.TimeoutError:
+                    pass
+                backoff_seconds = min(backoff_seconds * 2, 30.0)
+            finally:
+                if self._connection:
+                    try:
+                        await self._connection.remove_listener(self._channel, self._on_notification)
+                    except Exception:
+                        pass
+                    try:
+                        await self._connection.close()
+                    except Exception:
+                        pass
+                    self._connection = None
+
+    async def _poll_outbox(self) -> None:
+        if self._connection is None:
+            return
+
+        rows = await self._connection.fetch(
+            """
+            SELECT id, payload
+            FROM earth_data_change_events
+            WHERE consumed_at IS NULL
+            ORDER BY id
+            LIMIT $1
+            """,
+            OUTBOX_POLL_LIMIT,
+        )
+        accepted_count = 0
+        consumed_ids: list[int] = []
+        for row in rows:
+            payload = row["payload"]
+            if isinstance(payload, str):
+                try:
+                    payload = json.loads(payload)
+                except json.JSONDecodeError:
+                    consumed_ids.append(int(row["id"]))
+                    continue
+            if isinstance(payload, dict):
+                if self._dispatcher.handle_payload(payload):
+                    accepted_count += 1
+                consumed_ids.append(int(row["id"]))
+            else:
+                consumed_ids.append(int(row["id"]))
+        if consumed_ids:
+            await self._dispatcher.flush_all()
+        if consumed_ids:
+            await self._connection.execute(
+                """
+                UPDATE earth_data_change_events
+                SET consumed_at = NOW()
+                WHERE id = ANY($1::bigint[])
+                  AND consumed_at IS NULL
+                """,
+                consumed_ids,
+            )
+        if rows:
+            logger.info_event(
+                "Polled Earth database change outbox",
+                event="earth.db_changes.outbox_polled",
+                context={"events": len(rows), "accepted": accepted_count},
+            )
+
+    def _on_notification(
+        self,
+        _connection: asyncpg.Connection,
+        _pid: int,
+        _channel: str,
+        payload: str,
+    ) -> None:
+        if self._loop and self._loop.is_running():
+            self._loop.call_soon_threadsafe(self._dispatcher.handle_notification, payload)
+            return
+        self._dispatcher.handle_notification(payload)
+
+
+_dispatcher = EarthDbChangeDispatcher(
+    broadcast_earth_update=broadcaster.broadcast_earth_update,
+    invalidate_cache=invalidate_earth_layer_cache_for_source,
+)
+_listener: EarthDbChangeListener | None = None
+
+
+def start_earth_db_change_listener() -> None:
+    global _listener
+    if _listener is not None:
+        return
+    _listener = EarthDbChangeListener(dsn=settings.DATABASE_URL, dispatcher=_dispatcher)
+    _listener.start()
+
+
+async def stop_earth_db_change_listener() -> None:
+    global _listener
+    if _listener is None:
+        await _dispatcher.stop()
+        return
+    listener = _listener
+    _listener = None
+    await listener.stop()

backend/app/services/earth_interactables.py

@@ -0,0 +1,113 @@
+from __future__ import annotations
+
+from datetime import UTC, datetime
+from typing import Any
+from uuid import uuid4
+
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.core.time import to_iso8601_utc
+from app.core.websocket.broadcaster import broadcaster
+from app.models.earth_interactable import EarthInteractable
+from app.services.earth_layer_cache import EARTH_LAYER_CACHE_PREFIX, earth_layer_cache
+
+INTERACTABLE_ENTITY = "interactable"
+INTERACTABLE_LAYER = "interactables"
+
+
+def normalize_interactable_id(value: str | None = None) -> str:
+    raw = str(value or "").strip()
+    return raw or f"interactable-{uuid4().hex}"
+
+
+def serialize_interactable(record: EarthInteractable) -> dict[str, Any]:
+    return {
+        "id": record.id,
+        "layer": record.layer,
+        "kind": record.kind,
+        "label": record.label,
+        "description": record.description,
+        "latitude": record.latitude,
+        "longitude": record.longitude,
+        "altitude": record.altitude,
+        "revision": record.revision,
+        "properties": record.properties or {},
+        "is_deleted": bool(record.is_deleted),
+        "created_at": to_iso8601_utc(record.created_at),
+        "updated_at": to_iso8601_utc(record.updated_at),
+        "deleted_at": to_iso8601_utc(record.deleted_at),
+    }
+
+
+def interactables_to_geojson(items: list[EarthInteractable]) -> dict[str, Any]:
+    return {
+        "type": "FeatureCollection",
+        "features": [
+            {
+                "type": "Feature",
+                "id": item.id,
+                "geometry": {
+                    "type": "Point",
+                    "coordinates": [item.longitude, item.latitude],
+                },
+                "properties": serialize_interactable(item),
+            }
+            for item in items
+            if not item.is_deleted
+        ],
+    }
+
+
+def invalidate_interactable_cache(layer: str | None = None) -> int:
+    layer_key = str(layer or "*").strip() or "*"
+    deleted = earth_layer_cache.delete_pattern(
+        f"{EARTH_LAYER_CACHE_PREFIX}:interactables:layer:{layer_key}*"
+    )
+    if layer_key != "all":
+        deleted += earth_layer_cache.delete_pattern(
+            f"{EARTH_LAYER_CACHE_PREFIX}:interactables:layer:all*"
+        )
+    return deleted
+
+
+def build_interactable_event(
+    *,
+    action: str,
+    record: EarthInteractable,
+    include_item: bool = True,
+) -> dict[str, Any]:
+    item = serialize_interactable(record)
+    return {
+        "entity": INTERACTABLE_ENTITY,
+        "action": action,
+        "layer": record.layer,
+        "layers": [INTERACTABLE_LAYER],
+        "ids": [record.id],
+        "revision": record.revision,
+        "changed_at": item["deleted_at"] or item["updated_at"] or to_iso8601_utc(datetime.now(UTC)),
+        "item": item if include_item else None,
+        "source": "earth_interactables",
+    }
+
+
+async def publish_interactable_event(action: str, record: EarthInteractable, *, include_item: bool = True) -> None:
+    await broadcaster.broadcast_earth_update(
+        build_interactable_event(action=action, record=record, include_item=include_item)
+    )
+
+
+async def list_interactables(
+    db: AsyncSession,
+    *,
+    layer: str | None = None,
+    include_deleted: bool = False,
+) -> list[EarthInteractable]:
+    stmt = select(EarthInteractable)
+    if layer:
+        stmt = stmt.where(EarthInteractable.layer == layer)
+    if not include_deleted:
+        stmt = stmt.where(EarthInteractable.is_deleted.is_(False))
+    stmt = stmt.order_by(EarthInteractable.updated_at.desc(), EarthInteractable.id.asc())
+    result = await db.execute(stmt)
+    return list(result.scalars().all())

backend/app/services/earth_layer_adapters.py

@@ -0,0 +1,179 @@
+"""Earth layer adapter registry for datasource-backed refresh behavior."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from typing import Any
+
+from sqlalchemy.ext.asyncio import AsyncSession
+
+
+@dataclass(frozen=True)
+class EarthLayerAdapter:
+    sources: frozenset[str]
+    layers: tuple[str, ...]
+    cache_patterns: tuple[str, ...]
+    tables: frozenset[str] = field(default_factory=frozenset)
+    derived_models: tuple[str, ...] = field(default_factory=tuple)
+    refresh_strategy: str = "clear_then_reload"
+
+
+EARTH_LAYER_ADAPTERS: tuple[EarthLayerAdapter, ...] = (
+    EarthLayerAdapter(
+        sources=frozenset({"barentswatch_vessels", "aisstream_vessels", "vessel_static", "vessel_position", "ais_raw_observations", "ais_source_health"}),
+        tables=frozenset({"vessel_static", "vessel_position", "ais_raw_observations", "ais_source_health"}),
+        layers=("vessels",),
+        cache_patterns=("vessels*", "summary*"),
+    ),
+    EarthLayerAdapter(
+        sources=frozenset(
+            {
+                "telegeography_cables",
+                "telegeography_landing",
+                "telegeography_landing_points",
+                "telegeography_systems",
+                "telegeography_cable_systems",
+                "arcgis_cables",
+                "arcgis_landing_points",
+                "arcgis_cable_landing_relation",
+                "arcgis_cable_landing_relations",
+                "fao_landing_points",
+            }
+        ),
+        tables=frozenset({"collected_data"}),
+        layers=("cables",),
+        cache_patterns=("cables*", "landing-points*", "summary*"),
+    ),
+    EarthLayerAdapter(
+        sources=frozenset({"celestrak_tle", "spacetrack_tle"}),
+        tables=frozenset({"collected_data"}),
+        layers=("satellites",),
+        cache_patterns=("satellites*", "summary*"),
+    ),
+    EarthLayerAdapter(
+        sources=frozenset(
+            {
+                "top500",
+                "top500_supercomputers",
+                "epoch_ai_gpu",
+                "huggingface_models",
+                "huggingface_datasets",
+                "huggingface_spaces",
+                "compute_center_locations",
+            }
+        ),
+        tables=frozenset({"compute_center_locations"}),
+        layers=("computeCenters",),
+        cache_patterns=("compute-centers*", "summary*"),
+        refresh_strategy="reload",
+    ),
+    EarthLayerAdapter(
+        sources=frozenset(
+            {
+                "ris_live_bgp",
+                "bgpstream_bgp",
+                "iptoasn_prefix_geo",
+                "opengeofeed_prefix_geo",
+                "nro_delegated_prefix_geo",
+                "bgp_observations",
+                "bgp_anomalies",
+                "bgp_incidents",
+                "bgp_collector_locations",
+            }
+        ),
+        tables=frozenset({"bgp_observations", "bgp_anomalies", "bgp_incidents", "bgp_collector_locations"}),
+        layers=("bgp",),
+        cache_patterns=("bgp*", "summary*"),
+        derived_models=("bgp_observations", "bgp_anomalies", "bgp_incidents"),
+    ),
+    EarthLayerAdapter(
+        sources=frozenset({"news_live_streams"}),
+        tables=frozenset({"collected_data"}),
+        layers=("media",),
+        cache_patterns=("summary*",),
+        refresh_strategy="reload",
+    ),
+    EarthLayerAdapter(
+        sources=frozenset({"media_news_archive", "earth_news_items"}),
+        tables=frozenset({"earth_news_items"}),
+        layers=("news",),
+        cache_patterns=("summary*",),
+        refresh_strategy="reload",
+    ),
+    EarthLayerAdapter(
+        sources=frozenset({"earth_interactables"}),
+        tables=frozenset({"earth_interactables"}),
+        layers=("interactables",),
+        cache_patterns=("interactables*", "summary*"),
+        refresh_strategy="delta",
+    ),
+)
+
+_ADAPTERS_BY_SOURCE = {
+    source: adapter
+    for adapter in EARTH_LAYER_ADAPTERS
+    for source in adapter.sources
+}
+_ADAPTERS_BY_TABLE = {
+    table: adapter
+    for adapter in EARTH_LAYER_ADAPTERS
+    for table in adapter.tables
+}
+
+
+def get_earth_layer_adapter_for_source(source: str | None) -> EarthLayerAdapter | None:
+    return _ADAPTERS_BY_SOURCE.get(str(source or "").strip())
+
+
+def get_earth_layer_adapter_for_change(table: str | None, source: str | None) -> EarthLayerAdapter | None:
+    table_key = str(table or "").strip()
+    source_key = str(source or "").strip()
+    if table_key and table_key != "collected_data":
+        adapter = _ADAPTERS_BY_TABLE.get(table_key)
+        if adapter is not None:
+            return adapter
+    return get_earth_layer_adapter_for_source(source_key)
+
+
+def get_earth_update_layers_for_source(source: str | None) -> list[str]:
+    adapter = get_earth_layer_adapter_for_source(source)
+    return list(adapter.layers) if adapter else []
+
+
+def get_earth_update_layers_for_change(table: str | None, source: str | None) -> list[str]:
+    adapter = get_earth_layer_adapter_for_change(table, source)
+    return list(adapter.layers) if adapter else []
+
+
+def get_earth_refresh_strategy_for_change(table: str | None, source: str | None) -> str | None:
+    adapter = get_earth_layer_adapter_for_change(table, source)
+    return adapter.refresh_strategy if adapter else None
+
+
+def get_earth_cache_patterns_for_source(source: str | None) -> list[str]:
+    adapter = get_earth_layer_adapter_for_source(source)
+    return list(adapter.cache_patterns) if adapter else []
+
+
+async def clear_derived_datasource_data(db: AsyncSession, source: str) -> dict[str, int]:
+    adapter = get_earth_layer_adapter_for_source(source)
+    if adapter is None or not adapter.derived_models:
+        return {}
+
+    from app.models.bgp_anomaly import BGPAnomaly
+    from app.models.bgp_incident import BGPIncident
+    from app.models.bgp_observation import BGPObservation
+
+    model_by_key: dict[str, Any] = {
+        "bgp_observations": BGPObservation,
+        "bgp_anomalies": BGPAnomaly,
+        "bgp_incidents": BGPIncident,
+    }
+    deleted_counts: dict[str, int] = {}
+    for key in adapter.derived_models:
+        model = model_by_key.get(key)
+        if model is None:
+            continue
+        result = await db.execute(model.__table__.delete().where(model.source == source))
+        deleted_counts[key] = int(result.rowcount or 0)
+    return deleted_counts

backend/app/services/earth_layer_cache.py

@@ -0,0 +1,384 @@
+from __future__ import annotations
+
+import asyncio
+from collections.abc import Awaitable, Callable
+from dataclasses import dataclass
+import hashlib
+import json
+import time
+from typing import Any
+
+from fastapi import Response
+
+from app.core.cache import _RedisClient
+from app.core.config import settings
+from app.core.logging import get_logger
+
+
+logger = get_logger(__name__, service="earth_layer_cache")
+
+EARTH_LAYER_CACHE_PREFIX = "earth:layer:v1"
+EARTH_LAYER_LOCK_PREFIX = "earth:layer:lock:v1"
+DEFAULT_LOCK_TTL_SECONDS = 10
+DEFAULT_LOCK_WAIT_SECONDS = 0.2
+DEFAULT_MAX_FEATURES = 5000
+DEFAULT_MAX_BYTES = 5 * 1024 * 1024
+DEFAULT_BBOX_PRECISION_DEGREES = 0.1
+DEV_CACHE_KEY_HEADER = {"development", "dev", "test", "testing", "local"}
+
+
+@dataclass(frozen=True)
+class EarthLayerCachePolicy:
+    fresh_ttl_seconds: int
+    stale_ttl_seconds: int
+    max_features: int = DEFAULT_MAX_FEATURES
+    max_bytes: int = DEFAULT_MAX_BYTES
+    lock_ttl_seconds: int = DEFAULT_LOCK_TTL_SECONDS
+    lock_wait_seconds: float = DEFAULT_LOCK_WAIT_SECONDS
+
+
+@dataclass(frozen=True)
+class EarthLayerCacheResult:
+    payload: dict[str, Any]
+    state: str
+    key: str
+    features: int
+    bytes: int
+
+
+class EarthLayerCache:
+    def __init__(self) -> None:
+        self._client = None
+
+    @property
+    def client(self):
+        if self._client is None:
+            self._client = _RedisClient.get_client()
+        return self._client
+
+    @staticmethod
+    def key(layer: str, **params: Any) -> str:
+        parts = [EARTH_LAYER_CACHE_PREFIX, _safe_key_part(layer)]
+        for name in sorted(params):
+            value = params[name]
+            if value is None:
+                value = "none"
+            parts.append(f"{_safe_key_part(name)}:{_safe_key_part(value)}")
+        return ":".join(parts)
+
+    @staticmethod
+    def stale_key(key: str) -> str:
+        return f"{key}:stale"
+
+    @staticmethod
+    def lock_key(key: str) -> str:
+        digest = hashlib.sha256(key.encode("utf-8")).hexdigest()[:32]
+        return f"{EARTH_LAYER_LOCK_PREFIX}:{digest}"
+
+    def get_json(self, key: str) -> dict[str, Any] | None:
+        raw = self.client.get(key)
+        if not raw:
+            return None
+        value = json.loads(raw)
+        return value if isinstance(value, dict) else None
+
+    def set_json(self, key: str, payload: dict[str, Any], ttl_seconds: int) -> None:
+        self.client.setex(key, ttl_seconds, json.dumps(payload, ensure_ascii=False, default=str))
+
+    def acquire_lock(self, key: str, ttl_seconds: int) -> bool:
+        return bool(self.client.set(self.lock_key(key), "1", nx=True, ex=ttl_seconds))
+
+    def release_lock(self, key: str) -> None:
+        try:
+            self.client.delete(self.lock_key(key))
+        except Exception:
+            pass
+
+    def delete_pattern(self, pattern: str = f"{EARTH_LAYER_CACHE_PREFIX}:*") -> int:
+        keys = list(self.client.scan_iter(match=pattern))
+        if not keys:
+            return 0
+        return int(self.client.delete(*keys))
+
+    def status(self) -> dict[str, Any]:
+        keys = list(self.client.scan_iter(match=f"{EARTH_LAYER_CACHE_PREFIX}:*"))
+        by_layer: dict[str, dict[str, Any]] = {}
+        total_memory = 0
+        for key in keys:
+            key_str = key.decode("utf-8") if isinstance(key, bytes) else str(key)
+            layer = _layer_from_key(key_str)
+            entry = by_layer.setdefault(layer, {"keys": 0, "stale_keys": 0, "memory_bytes": 0})
+            entry["keys"] += 1
+            if key_str.endswith(":stale"):
+                entry["stale_keys"] += 1
+            try:
+                memory = int(self.client.memory_usage(key) or 0)
+            except Exception:
+                memory = 0
+            entry["memory_bytes"] += memory
+            total_memory += memory
+        return {
+            "prefix": EARTH_LAYER_CACHE_PREFIX,
+            "key_count": len(keys),
+            "memory_bytes": total_memory,
+            "layers": by_layer,
+        }
+
+
+earth_layer_cache = EarthLayerCache()
+
+
+def quantize_bbox(
+    bbox: tuple[float, float, float, float],
+    *,
+    precision: float = DEFAULT_BBOX_PRECISION_DEGREES,
+) -> tuple[float, float, float, float]:
+    return tuple(round(value / precision) * precision for value in bbox)  # type: ignore[return-value]
+
+
+def format_bbox_key(bbox: tuple[float, float, float, float]) -> str:
+    return ",".join(f"{value:.1f}" for value in bbox)
+
+
+def apply_cache_headers(response: Response | None, result: EarthLayerCacheResult) -> None:
+    if response is None:
+        return
+    response.headers["X-Planet-Cache"] = result.state
+    response.headers["X-Planet-Cache-Features"] = str(result.features)
+    response.headers["X-Planet-Cache-Bytes"] = str(result.bytes)
+    env_name = str(getattr(settings, "ENVIRONMENT", "") or "development").lower()
+    if env_name in DEV_CACHE_KEY_HEADER:
+        response.headers["X-Planet-Cache-Key"] = result.key
+
+
+async def get_or_build_layer_payload(
+    *,
+    key: str,
+    policy: EarthLayerCachePolicy,
+    builder: Callable[[], Awaitable[dict[str, Any]]],
+    response: Response | None = None,
+) -> dict[str, Any]:
+    result = await resolve_layer_payload(key=key, policy=policy, builder=builder)
+    apply_cache_headers(response, result)
+    return result.payload
+
+
+async def resolve_layer_payload(
+    *,
+    key: str,
+    policy: EarthLayerCachePolicy,
+    builder: Callable[[], Awaitable[dict[str, Any]]],
+) -> EarthLayerCacheResult:
+    started = time.perf_counter()
+    try:
+        cached = earth_layer_cache.get_json(key)
+        if cached is not None:
+            return _result(cached, state="hit", key=key)
+
+        lock_acquired = earth_layer_cache.acquire_lock(key, policy.lock_ttl_seconds)
+        if lock_acquired:
+            try:
+                payload = await _build_budgeted_payload(builder, policy)
+                _write_fresh_and_stale(key, payload, policy)
+                _log_cache_event("refresh", key, payload, started)
+                return _result(payload, state="refresh", key=key)
+            except Exception as exc:
+                stale = _read_stale(key)
+                if stale is not None:
+                    logger.warning_event(
+                        "Earth layer cache builder failed; returning stale payload",
+                        event="earth_layer_cache.stale_after_builder_error",
+                        context={"key": key, "error": str(exc)},
+                    )
+                    return _result(stale, state="stale", key=key)
+                raise
+            finally:
+                earth_layer_cache.release_lock(key)
+
+        stale = _read_stale(key)
+        if stale is not None:
+            return _result(stale, state="stale", key=key)
+
+        await asyncio.sleep(policy.lock_wait_seconds)
+        cached_after_wait = earth_layer_cache.get_json(key)
+        if cached_after_wait is not None:
+            return _result(cached_after_wait, state="hit", key=key)
+
+        payload = await _build_budgeted_payload(builder, policy)
+        _log_cache_event("miss", key, payload, started)
+        return _result(payload, state="miss", key=key)
+    except Exception as exc:
+        try:
+            payload = await _build_budgeted_payload(builder, policy)
+        except Exception:
+            raise exc
+        logger.warning_event(
+            "Earth layer cache bypassed",
+            event="earth_layer_cache.bypass",
+            context={"key": key, "error": str(exc)},
+        )
+        return _result(payload, state="bypass", key=key)
+
+
+def apply_payload_budget(payload: dict[str, Any], policy: EarthLayerCachePolicy) -> dict[str, Any]:
+    budgeted = _truncate_features(payload, policy.max_features, "feature_budget")
+    size = _payload_size(budgeted)
+    if size <= policy.max_bytes:
+        return budgeted
+
+    features = budgeted.get("features")
+    if not isinstance(features, list):
+        return _with_budget_diagnostics(
+            budgeted,
+            truncated=True,
+            reason="byte_budget",
+            bytes_before=size,
+            bytes_after=size,
+        )
+
+    low = 0
+    high = len(features)
+    best = []
+    best_size = _payload_size({**budgeted, "features": best})
+    while low <= high:
+        mid = (low + high) // 2
+        candidate_features = features[:mid]
+        candidate = _with_budget_diagnostics(
+            {**budgeted, "features": candidate_features},
+            truncated=mid < len(features),
+            reason="byte_budget",
+            bytes_before=size,
+            bytes_after=0,
+        )
+        candidate_size = _payload_size(candidate)
+        if candidate_size <= policy.max_bytes:
+            best = candidate_features
+            best_size = candidate_size
+            low = mid + 1
+        else:
+            high = mid - 1
+
+    return _with_budget_diagnostics(
+        {**budgeted, "features": best},
+        truncated=True,
+        reason="byte_budget",
+        bytes_before=size,
+        bytes_after=best_size,
+    )
+
+
+def invalidate_earth_layer_cache_for_source(source: str) -> int:
+    from app.services.earth_layer_adapters import get_earth_cache_patterns_for_source
+
+    source_key = str(source or "").strip()
+    patterns = get_earth_cache_patterns_for_source(source_key)
+    deleted = 0
+    for layer_pattern in patterns:
+        deleted += earth_layer_cache.delete_pattern(f"{EARTH_LAYER_CACHE_PREFIX}:{layer_pattern}")
+    return deleted
+
+
+async def _build_budgeted_payload(
+    builder: Callable[[], Awaitable[dict[str, Any]]],
+    policy: EarthLayerCachePolicy,
+) -> dict[str, Any]:
+    payload = await builder()
+    return apply_payload_budget(payload, policy)
+
+
+def _write_fresh_and_stale(key: str, payload: dict[str, Any], policy: EarthLayerCachePolicy) -> None:
+    earth_layer_cache.set_json(key, payload, policy.fresh_ttl_seconds)
+    earth_layer_cache.set_json(earth_layer_cache.stale_key(key), payload, policy.stale_ttl_seconds)
+
+
+def _read_stale(key: str) -> dict[str, Any] | None:
+    try:
+        return earth_layer_cache.get_json(earth_layer_cache.stale_key(key))
+    except Exception:
+        return None
+
+
+def _truncate_features(payload: dict[str, Any], max_features: int, reason: str) -> dict[str, Any]:
+    features = payload.get("features")
+    if not isinstance(features, list) or len(features) <= max_features:
+        return payload
+    return _with_budget_diagnostics(
+        {**payload, "features": features[:max_features]},
+        truncated=True,
+        reason=reason,
+        original_feature_count=len(features),
+    )
+
+
+def _with_budget_diagnostics(
+    payload: dict[str, Any],
+    *,
+    truncated: bool,
+    reason: str,
+    original_feature_count: int | None = None,
+    bytes_before: int | None = None,
+    bytes_after: int | None = None,
+) -> dict[str, Any]:
+    diagnostics = dict(payload.get("diagnostics") or {})
+    diagnostics.update(
+        {
+            "truncated": bool(truncated or diagnostics.get("truncated")),
+            "limit_reason": reason,
+        }
+    )
+    if original_feature_count is not None:
+        diagnostics["original_feature_count"] = original_feature_count
+    if bytes_before is not None:
+        diagnostics["bytes_before_budget"] = bytes_before
+    if bytes_after is not None:
+        diagnostics["bytes_after_budget"] = bytes_after
+    return {**payload, "diagnostics": diagnostics}
+
+
+def _result(payload: dict[str, Any], *, state: str, key: str) -> EarthLayerCacheResult:
+    return EarthLayerCacheResult(
+        payload=payload,
+        state=state,
+        key=key,
+        features=_feature_count(payload),
+        bytes=_payload_size(payload),
+    )
+
+
+def _feature_count(payload: dict[str, Any]) -> int:
+    features = payload.get("features")
+    if isinstance(features, list):
+        return len(features)
+    count = payload.get("count")
+    return int(count) if isinstance(count, int) else 0
+
+
+def _payload_size(payload: dict[str, Any]) -> int:
+    return len(json.dumps(payload, ensure_ascii=False, default=str).encode("utf-8"))
+
+
+def _safe_key_part(value: Any) -> str:
+    raw = str(value).strip().lower()
+    return "".join(char if char.isalnum() or char in {"-", "_", ".", ","} else "_" for char in raw)[:160]
+
+
+def _layer_from_key(key: str) -> str:
+    prefix = f"{EARTH_LAYER_CACHE_PREFIX}:"
+    if not key.startswith(prefix):
+        return "unknown"
+    remainder = key[len(prefix):]
+    return remainder.split(":", 1)[0]
+
+
+def _log_cache_event(state: str, key: str, payload: dict[str, Any], started: float) -> None:
+    logger.info_event(
+        "Earth layer cache resolved",
+        event="earth_layer_cache.resolved",
+        context={
+            "state": state,
+            "key": key,
+            "features": _feature_count(payload),
+            "bytes": _payload_size(payload),
+            "duration_ms": round((time.perf_counter() - started) * 1000, 2),
+        },
+    )

backend/app/services/earth_news.py

@@ -1,11 +1,13 @@
 from __future__ import annotations
 
 import asyncio
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from datetime import UTC, datetime
 from email.utils import parsedate_to_datetime
 import hashlib
 import html
+import json
+import math
 import re
 from typing import Any
 from urllib.parse import quote
@@ -13,6 +15,13 @@ import xml.etree.ElementTree as ET
 
 import httpx
 from bs4 import BeautifulSoup
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.core.countries import COUNTRY_VARIANTS_MAP, get_country_centroid, normalize_country
+from app.ai_tasks.prompts import EffectiveAIPrompt, get_effective_prompt
+from app.schemas.ai import SituationalAnalysisRequest
+from app.services.ai_client import AIProviderClient
+from app.services.location.resolvers.nominatim import build_default_nominatim_geocoder
 
 
 USER_AGENT = "PlanetEarthNewsBoard/1.0 (+https://planet.local)"
@@ -20,6 +29,11 @@ REQUEST_TIMEOUT = 12.0
 MAX_ITEMS_PER_SOURCE = 6
 MAX_ITEMS_TOTAL = 12
 STALE_CACHE_MAX_AGE_SECONDS = 60 * 45
+RSS_SUPPLEMENT_MAX_AGE_SECONDS = STALE_CACHE_MAX_AGE_SECONDS
+MAX_TARGET_INFERENCE_CONCURRENCY = 3
+TARGET_INFERENCE_TIMEOUT_SECONDS = 6.0
+DEFAULT_NEWS_LOCALE = "zh-CN"
+NEWS_ENRICH_PROMPT_KEY = "earth.news.enrich"
 
 
 @dataclass(frozen=True)
@@ -49,6 +63,17 @@ class NewsFeedSource:
     priority: int = 100
 
 
+@dataclass(frozen=True)
+class NewsTargetLocation:
+    latitude: float
+    longitude: float
+    label: str
+    source: str
+    confidence: float | None = None
+    country: str | None = None
+    city: str | None = None
+
+
 @dataclass
 class ParsedNewsItem:
     id: str
@@ -60,6 +85,18 @@ class ParsedNewsItem:
     feed_region: str
     homepage_url: str
     published_at: datetime | None
+    content_language: str = "en"
+    localizations: dict[str, dict[str, str]] = field(default_factory=dict)
+    enrichment_status: str = "pending"
+    enrichment_error: str | None = None
+    enriched_at: datetime | None = None
+    target_location: NewsTargetLocation | None = None
+    target_resolution_stage: str = "unresolved"
+    target_ai_attempted: bool = False
+    target_ai_status: str = "not_attempted"
+    target_ai_error: str | None = None
+    target_debug_note: str | None = None
+    location_patch: dict[str, Any] | None = None
 
 
 @dataclass
@@ -236,6 +273,17 @@ NEWS_FEED_SOURCES: tuple[NewsFeedSource, ...] = (
 
 
 _REGION_CACHE: dict[str, CachedRegionFeed] = {}
+_news_target_geocode = build_default_nominatim_geocoder(user_agent=USER_AGENT)
+_CITY_HINTS: tuple[dict[str, str | None], ...] = (
+    {"name": "Beijing", "country": "中国"},
+    {"name": "Havana", "country": "古巴"},
+    {"name": "Kyiv", "country": "乌克兰"},
+    {"name": "Bangkok", "country": "泰国"},
+    {"name": "Tehran", "country": "伊朗"},
+    {"name": "Moscow", "country": "俄罗斯"},
+    {"name": "Taipei", "country": "中国（台湾）"},
+    {"name": "Hong Kong", "country": "中国（香港）"},
+)
 
 
 def determine_focus_region(lat: float | None, lon: float | None) -> str:
@@ -258,6 +306,462 @@ def get_region_anchor(region: str) -> RegionAnchor:
     return REGION_ANCHORS.get(region, REGION_ANCHORS["global"])
 
 
+def _coerce_str(value: Any) -> str | None:
+    if value is None:
+        return None
+    if not isinstance(value, str):
+        value = str(value)
+    cleaned = re.sub(r"\s+", " ", value).strip()
+    return cleaned or None
+
+
+def _contains_location_alias(text: str, alias: str) -> bool:
+    normalized_alias = _coerce_str(alias)
+    if not normalized_alias:
+        return False
+    if re.search(r"[A-Za-z]", normalized_alias):
+        pattern = r"(?<![A-Za-z])" + re.escape(normalized_alias) + r"(?![A-Za-z])"
+        return re.search(pattern, text, flags=re.IGNORECASE) is not None
+    return normalized_alias in text
+
+
+def _iter_searchable_country_variants(
+    canonical: str,
+    variants: list[str],
+) -> tuple[str, ...]:
+    searchable: list[str] = []
+    seen: set[str] = set()
+    for variant in (canonical, *variants):
+        normalized = _coerce_str(variant)
+        if not normalized:
+            continue
+        if re.fullmatch(r"[A-Z]{2,3}", normalized):
+            continue
+        if len(normalized) <= 2:
+            continue
+        key = normalized.casefold()
+        if key in seen:
+            continue
+        seen.add(key)
+        searchable.append(normalized)
+    return tuple(searchable)
+
+
+def _coerce_float(value: Any) -> float | None:
+    try:
+        parsed = float(value)
+    except (TypeError, ValueError):
+        return None
+    if not math.isfinite(parsed):
+        return None
+    return parsed
+
+
+def _first_json_object(text: str) -> dict[str, Any] | None:
+    if not text:
+        return None
+    decoder = json.JSONDecoder()
+    for index, char in enumerate(text):
+        if char != "{":
+            continue
+        try:
+            payload, _ = decoder.raw_decode(text[index:])
+        except ValueError:
+            continue
+        if isinstance(payload, dict):
+            return payload
+    return None
+
+
+def _normalize_localizations(value: Any) -> dict[str, dict[str, str]]:
+    if not isinstance(value, dict):
+        return {}
+    normalized: dict[str, dict[str, str]] = {}
+    for locale, payload in value.items():
+        locale_key = _coerce_str(locale)
+        if not locale_key or not isinstance(payload, dict):
+            continue
+        title = _coerce_str(payload.get("title"))
+        summary = _coerce_str(payload.get("summary"))
+        entry: dict[str, str] = {}
+        if title:
+            entry["title"] = title
+        if summary:
+            entry["summary"] = summary
+        if entry:
+            normalized[locale_key] = entry
+    return normalized
+
+
+def _get_locale_text(
+    item: ParsedNewsItem,
+    key: str,
+    *,
+    locale: str = DEFAULT_NEWS_LOCALE,
+) -> str:
+    localized = item.localizations.get(locale)
+    if isinstance(localized, dict):
+        value = _coerce_str(localized.get(key))
+        if value:
+            return value
+    return ""
+
+
+def _has_default_localization(item: ParsedNewsItem) -> bool:
+    localized = item.localizations.get(DEFAULT_NEWS_LOCALE)
+    if not isinstance(localized, dict):
+        return False
+    return bool(_coerce_str(localized.get("title")) and _coerce_str(localized.get("summary")))
+
+
+def apply_enrichment_patch_to_item(
+    item: ParsedNewsItem,
+    patch: dict[str, Any],
+) -> ParsedNewsItem:
+    item.location_patch = patch
+    if "content_language" in patch:
+        item.content_language = _coerce_str(patch.get("content_language")) or item.content_language
+    if "localizations" in patch:
+        item.localizations = _normalize_localizations(patch.get("localizations"))
+    if "enrichment_status" in patch:
+        item.enrichment_status = _coerce_str(patch.get("enrichment_status")) or item.enrichment_status
+    if "enrichment_error" in patch:
+        item.enrichment_error = _coerce_str(patch.get("enrichment_error"))
+    if "enriched_at" in patch:
+        item.enriched_at = _parse_datetime(_coerce_str(patch.get("enriched_at")))
+    return item
+
+
+async def _geocode_target_location(query: str) -> dict[str, Any] | None:
+    return await asyncio.to_thread(_news_target_geocode, query)
+
+
+async def _build_target_location_from_payload(
+    payload: dict[str, Any],
+) -> NewsTargetLocation | None:
+    country = normalize_country(payload.get("country"))
+    city = _coerce_str(payload.get("city"))
+    matched_location_name = _coerce_str(payload.get("matched_location_name"))
+    confidence = _coerce_float(payload.get("confidence"))
+    if confidence is not None:
+        confidence = max(0.0, min(confidence, 1.0))
+
+    latitude = _coerce_float(payload.get("latitude"))
+    longitude = _coerce_float(payload.get("longitude"))
+    if latitude not in (None, 0.0) and longitude not in (None, 0.0):
+        label = matched_location_name or ", ".join(part for part in (city, country) if part) or "关联位置"
+        return NewsTargetLocation(
+            latitude=latitude,
+            longitude=longitude,
+            label=label,
+            source="ai_inferred_target",
+            confidence=confidence,
+            country=country,
+            city=city,
+        )
+
+    geocode_queries: list[str] = []
+    for value in (
+        ", ".join(part for part in (city, country) if part),
+        matched_location_name,
+        city,
+        country,
+    ):
+        normalized = _coerce_str(value)
+        if normalized and normalized not in geocode_queries:
+            geocode_queries.append(normalized)
+
+    for query in geocode_queries:
+        try:
+            result = await _geocode_target_location(query)
+        except Exception:
+            continue
+        if not isinstance(result, dict):
+            continue
+        latitude = _coerce_float(result.get("lat"))
+        longitude = _coerce_float(result.get("lon"))
+        if latitude in (None, 0.0) or longitude in (None, 0.0):
+            continue
+        label = (
+            _coerce_str(result.get("display_name"))
+            or matched_location_name
+            or ", ".join(part for part in (city, country) if part)
+            or query
+        )
+        return NewsTargetLocation(
+            latitude=latitude,
+            longitude=longitude,
+            label=label,
+            source="ai_inferred_target",
+            confidence=confidence,
+            country=country,
+            city=city,
+        )
+
+    centroid = get_country_centroid(country)
+    if centroid:
+        label = matched_location_name or city or country or "关联位置"
+        return NewsTargetLocation(
+            latitude=centroid["latitude"],
+            longitude=centroid["longitude"],
+            label=label,
+            source="ai_inferred_target",
+            confidence=confidence,
+            country=country,
+            city=city,
+        )
+
+    return None
+
+
+async def _extract_target_location_from_text(item: ParsedNewsItem) -> NewsTargetLocation | None:
+    combined_text = " ".join(part for part in (item.title, item.summary) if part).strip()
+    if not combined_text:
+        return None
+
+    for hint in _CITY_HINTS:
+        city_name = _coerce_str(hint.get("name"))
+        if not city_name or not _contains_location_alias(combined_text, city_name):
+            continue
+        country = normalize_country(hint.get("country"))
+        geocode_query = ", ".join(part for part in (city_name, country) if part)
+        try:
+            result = await _geocode_target_location(geocode_query)
+        except Exception:
+            result = None
+        if isinstance(result, dict):
+            latitude = _coerce_float(result.get("lat"))
+            longitude = _coerce_float(result.get("lon"))
+            if latitude not in (None, 0.0) and longitude not in (None, 0.0):
+                return NewsTargetLocation(
+                    latitude=latitude,
+                    longitude=longitude,
+                    label=_coerce_str(result.get("display_name")) or geocode_query,
+                    source="headline_location_hint",
+                    confidence=0.78,
+                    country=country,
+                    city=city_name,
+                )
+        centroid = get_country_centroid(country)
+        if centroid:
+            return NewsTargetLocation(
+                latitude=centroid["latitude"],
+                longitude=centroid["longitude"],
+                label=geocode_query,
+                source="headline_location_hint",
+                confidence=0.68,
+                country=country,
+                city=city_name,
+            )
+
+    for canonical, variants in COUNTRY_VARIANTS_MAP.items():
+        if not get_country_centroid(canonical):
+            continue
+        searchable_variants = _iter_searchable_country_variants(canonical, variants)
+        if not any(_contains_location_alias(combined_text, variant) for variant in searchable_variants):
+            continue
+        centroid = get_country_centroid(canonical)
+        if not centroid:
+            continue
+        return NewsTargetLocation(
+            latitude=centroid["latitude"],
+            longitude=centroid["longitude"],
+            label=canonical,
+            source="headline_country_hint",
+            confidence=0.62,
+            country=canonical,
+            city=None,
+        )
+
+    return None
+
+
+async def _infer_news_target_location(
+    item: ParsedNewsItem,
+    *,
+    provider_client: AIProviderClient | None,
+    prompt: EffectiveAIPrompt | None = None,
+) -> NewsTargetLocation | None:
+    target, _localizations = await _infer_news_enrichment(
+        item,
+        provider_client=provider_client,
+        prompt=prompt,
+    )
+    return target
+
+
+async def _infer_news_enrichment(
+    item: ParsedNewsItem,
+    *,
+    provider_client: AIProviderClient | None,
+    prompt: EffectiveAIPrompt | None = None,
+) -> tuple[NewsTargetLocation | None, dict[str, dict[str, str]]]:
+    text_hint = await _extract_target_location_from_text(item)
+    content_error: str | None = None
+    if text_hint is not None and text_hint.city:
+        item.target_resolution_stage = text_hint.source
+        item.target_ai_attempted = False
+        item.target_ai_status = "skipped_text_hint"
+        item.target_ai_error = None
+        item.target_debug_note = f"text hint matched {text_hint.label}"
+    localizations: dict[str, dict[str, str]] = {}
+
+    if provider_client is None:
+        if text_hint is None or not text_hint.city:
+            item.target_resolution_stage = text_hint.source if text_hint is not None else "unresolved"
+            item.target_ai_attempted = False
+            item.target_ai_status = "unavailable"
+            item.target_ai_error = "AI provider is not configured or unavailable for earth-feed."
+            item.target_debug_note = (
+                f"text hint matched {text_hint.label}" if text_hint is not None else "no text location hint matched"
+            )
+        item.enrichment_status = "unavailable"
+        item.enrichment_error = "AI provider is not configured or unavailable for earth-feed."
+        return text_hint, localizations
+
+    if text_hint is None or not text_hint.city:
+        item.target_ai_attempted = True
+        item.target_ai_status = "attempted"
+        item.target_ai_error = None
+        item.target_debug_note = (
+            f"text hint matched {text_hint.label}" if text_hint is not None else "no text location hint matched"
+        )
+    item.enrichment_status = "attempted"
+    item.enrichment_error = None
+
+    prompt = prompt or await get_effective_prompt(None, NEWS_ENRICH_PROMPT_KEY)
+    request = SituationalAnalysisRequest(
+        title="Enrich Earth news item with event location and zh-CN content",
+        objective=prompt.prompt,
+        system_prompt=prompt.system_prompt or None,
+        context={
+            "news_item": {
+                "title": item.title,
+                "summary": item.summary,
+                "source": item.source,
+                "feed_name": item.feed_name,
+                "feed_region": item.feed_region,
+                "url": item.url,
+                "published_at": (
+                    item.published_at.isoformat().replace("+00:00", "Z")
+                    if item.published_at
+                    else None
+                ),
+            },
+            "required_json_schema": {
+                "location": {
+                    "country": "string|null",
+                    "city": "string|null",
+                    "matched_location_name": "string|null",
+                    "latitude": "number|null",
+                    "longitude": "number|null",
+                    "confidence": "number from 0 to 1",
+                    "reasoning_summary": "short string",
+                },
+                "localizations": {
+                    "zh-CN": {
+                        "title": "faithful Simplified Chinese title",
+                        "summary": "one-sentence newswire-style Simplified Chinese lead summary",
+                    }
+                },
+            },
+        },
+        constraints=[
+            "Return only strict JSON. Do not wrap it in markdown.",
+            "For localizations, do not add facts that are absent from the RSS headline, description, source, or date.",
+            "Write zh-CN summary as one concise newswire-style sentence, like a breaking-news lead.",
+            "If the RSS description is thin, write a conservative one-sentence summary that says only what is supported.",
+            "Keep zh-CN summary factual, non-promotional, and avoid colon-heavy keyword labels.",
+            "Prefer the event location, not the newsroom or publisher headquarters.",
+            "When a country visit or summit is the clear topic but the city is omitted, use the most likely host city only if it is broadly public knowledge.",
+            "Use null for unknown fields instead of inventing details.",
+            "Calibrate confidence conservatively: 0.75+ only when the city is strongly supported, 0.55-0.74 for country-level or likely city inference, below 0.55 when weak.",
+        ],
+    )
+    try:
+        response = await provider_client.analyze(request)
+    except Exception as exc:
+        if text_hint is None or not text_hint.city:
+            item.target_resolution_stage = text_hint.source if text_hint is not None else "unresolved"
+            item.target_ai_status = "provider_error"
+            item.target_ai_error = str(exc)
+        item.enrichment_status = "provider_error"
+        item.enrichment_error = str(exc)
+        return text_hint, localizations
+
+    payload = _first_json_object(response.content)
+    if not isinstance(payload, dict):
+        if text_hint is None or not text_hint.city:
+            item.target_resolution_stage = text_hint.source if text_hint is not None else "unresolved"
+            item.target_ai_status = "parse_error"
+            item.target_ai_error = "AI response did not contain a parseable JSON object."
+        item.enrichment_status = "parse_error"
+        item.enrichment_error = "AI response did not contain a parseable JSON object."
+        return text_hint, localizations
+
+    localizations = _normalize_localizations(payload.get("localizations"))
+    if not localizations:
+        content_error = "AI returned no usable localizations."
+
+    location_payload = payload.get("location") if isinstance(payload.get("location"), dict) else payload
+    if text_hint is not None and text_hint.city:
+        target = text_hint
+    else:
+        target = await _build_target_location_from_payload(location_payload)
+    if target is None:
+        item.target_resolution_stage = text_hint.source if text_hint is not None else "unresolved"
+        item.target_ai_status = "no_result"
+        item.target_ai_error = "AI returned no usable target coordinates or geocodeable location."
+        target = text_hint
+    elif target.confidence is not None and target.confidence < 0.45:
+        item.target_resolution_stage = text_hint.source if text_hint is not None else "unresolved"
+        item.target_ai_status = "low_confidence"
+        item.target_ai_error = f"AI target confidence too low: {target.confidence:.2f}"
+        target = text_hint
+    else:
+        item.target_resolution_stage = target.source
+        item.target_ai_status = "success"
+        item.target_ai_error = None
+        item.target_debug_note = f"ai inferred {target.label}"
+
+    item.localizations = localizations
+    if localizations and item.target_ai_status in {"success", "skipped_text_hint"}:
+        item.enrichment_status = "success"
+        item.enrichment_error = None
+    elif localizations:
+        item.enrichment_status = "content_only"
+        item.enrichment_error = item.target_ai_error
+    else:
+        item.enrichment_status = "location_only" if target is not None else "no_result"
+        item.enrichment_error = content_error or item.target_ai_error
+    item.enriched_at = datetime.now(UTC) if localizations else None
+    return target, localizations
+
+
+async def _enrich_items_with_target_locations(
+    items: list[ParsedNewsItem],
+    *,
+    provider_client: AIProviderClient | None,
+    prompt: EffectiveAIPrompt | None = None,
+) -> list[ParsedNewsItem]:
+    if not items:
+        return items
+
+    semaphore = asyncio.Semaphore(MAX_TARGET_INFERENCE_CONCURRENCY)
+
+    async def enrich(item: ParsedNewsItem) -> ParsedNewsItem:
+        async with semaphore:
+            target = await _infer_news_target_location(
+                item,
+                provider_client=provider_client,
+                prompt=prompt,
+            )
+        item.target_location = target
+        return item
+
+    return list(await asyncio.gather(*(enrich(item) for item in items)))
+
+
 def get_sources_for_region(region: str) -> list[NewsFeedSource]:
     return sorted(
         [source for source in NEWS_FEED_SOURCES if source.region in {"global", region}],
@@ -349,7 +853,7 @@ def _parse_feed_entries(xml_text: str, source: NewsFeedSource) -> list[ParsedNew
         if not clean_title or not link:
             continue
 
-        item_source = _normalize_source_name(clean_title, source.name)
+        item_source = source.name
         display_title = clean_title
         if source.source_type == "aggregated" and " - " in clean_title:
             parts = clean_title.rsplit(" - ", 1)
@@ -385,23 +889,170 @@ def _serialize_sources(sources: list[NewsFeedSource]) -> list[dict[str, Any]]:
     ]
 
 
-def _serialize_item(item: ParsedNewsItem, *, active_region: str) -> dict[str, Any]:
-    published_at = item.published_at
+def _serialize_anchor(anchor: RegionAnchor) -> dict[str, Any]:
+    return {
+        "region": anchor.region,
+        "label": anchor.label,
+        "latitude": anchor.latitude,
+        "longitude": anchor.longitude,
+    }
+
+
+def _serialize_target(target: NewsTargetLocation | None) -> dict[str, Any] | None:
+    if target is None:
+        return None
+    return {
+        "latitude": target.latitude,
+        "longitude": target.longitude,
+        "label": target.label,
+        "source": target.source,
+        "confidence": target.confidence,
+        "country": target.country,
+        "city": target.city,
+    }
+
+
+def _serialize_enriched_at(value: datetime | None) -> str | None:
+    return value.isoformat().replace("+00:00", "Z") if value else None
+
+
+def _content_patch(item: ParsedNewsItem) -> dict[str, Any]:
+    return {
+        "content_language": item.content_language,
+        "localizations": item.localizations,
+        "enrichment_status": item.enrichment_status,
+        "enrichment_error": item.enrichment_error,
+        "enriched_at": _serialize_enriched_at(item.enriched_at),
+    }
+
+
+def build_anchor_location_patch(
+    item: ParsedNewsItem,
+    *,
+    queued: bool = False,
+    queue_available: bool | None = None,
+) -> dict[str, Any]:
     anchor = get_region_anchor(item.feed_region)
+    if queued:
+        resolution_stage = "queued"
+        ai_status = "queued"
+        debug_note = "queued for async target location inference"
+    else:
+        resolution_stage = item.target_resolution_stage
+        ai_status = item.target_ai_status
+        debug_note = item.target_debug_note
+    content_patch = _content_patch(item)
+    if queued and content_patch["enrichment_status"] == "pending":
+        content_patch["enrichment_status"] = "queued"
+    return {
+        "latitude": anchor.latitude,
+        "longitude": anchor.longitude,
+        "location_label": anchor.label,
+        "location_source": "region_anchor",
+        "verified": False,
+        "location_meta": {
+            "resolution_stage": resolution_stage,
+            "ai_attempted": item.target_ai_attempted,
+            "ai_status": ai_status,
+            "ai_error": item.target_ai_error,
+            "debug_note": debug_note,
+            "queue_available": queue_available,
+            "target": None,
+            "anchor": _serialize_anchor(anchor),
+        },
+        **content_patch,
+    }
+
+
+def build_target_location_patch(item: ParsedNewsItem, target: NewsTargetLocation | None) -> dict[str, Any]:
+    if target is None:
+        return build_anchor_location_patch(item)
+    anchor = get_region_anchor(item.feed_region)
+    return {
+        "latitude": target.latitude,
+        "longitude": target.longitude,
+        "location_label": target.label,
+        "location_source": target.source,
+        "verified": True,
+        "location_meta": {
+            "resolution_stage": item.target_resolution_stage,
+            "ai_attempted": item.target_ai_attempted,
+            "ai_status": item.target_ai_status,
+            "ai_error": item.target_ai_error,
+            "debug_note": item.target_debug_note,
+            "target": _serialize_target(target),
+            "anchor": _serialize_anchor(anchor),
+        },
+        **_content_patch(item),
+    }
+
+
+def build_target_location_job_payload(item: ParsedNewsItem) -> dict[str, Any]:
+    published_at = item.published_at
     return {
         "id": item.id,
         "title": item.title,
         "summary": item.summary,
+        "content_language": item.content_language,
+        "localizations": item.localizations,
+        "enrichment_status": item.enrichment_status,
+        "enrichment_error": item.enrichment_error,
+        "enriched_at": _serialize_enriched_at(item.enriched_at),
+        "url": item.url,
+        "source": item.source,
+        "feed_name": item.feed_name,
+        "feed_region": item.feed_region,
+        "homepage_url": item.homepage_url,
+        "published_at": published_at.isoformat().replace("+00:00", "Z") if published_at else None,
+    }
+
+
+def parsed_news_item_from_job_payload(payload: dict[str, Any]) -> ParsedNewsItem:
+    return ParsedNewsItem(
+        id=str(payload.get("id") or ""),
+        title=str(payload.get("title") or ""),
+        summary=str(payload.get("summary") or ""),
+        content_language=str(payload.get("content_language") or "en"),
+        localizations=_normalize_localizations(payload.get("localizations")),
+        enrichment_status=str(payload.get("enrichment_status") or "pending"),
+        enrichment_error=_coerce_str(payload.get("enrichment_error")),
+        enriched_at=_parse_datetime(_coerce_str(payload.get("enriched_at"))),
+        url=str(payload.get("url") or ""),
+        source=str(payload.get("source") or ""),
+        feed_name=str(payload.get("feed_name") or ""),
+        feed_region=str(payload.get("feed_region") or "global"),
+        homepage_url=str(payload.get("homepage_url") or ""),
+        published_at=_parse_datetime(_coerce_str(payload.get("published_at"))),
+    )
+
+
+def _serialize_item(item: ParsedNewsItem, *, active_region: str) -> dict[str, Any]:
+    published_at = item.published_at
+    location_patch = item.location_patch or build_target_location_patch(item, item.target_location)
+    return {
+        "id": item.id,
+        "title": item.title,
+        "summary": item.summary,
+        "content_language": item.content_language,
+        "localizations": item.localizations,
+        "display_title": _get_locale_text(item, "title"),
+        "display_summary": _get_locale_text(item, "summary"),
         "url": item.url,
         "source": item.source,
         "feed_name": item.feed_name,
         "region": item.feed_region,
+        "display_region": get_region_anchor(item.feed_region).label,
         "homepage_url": item.homepage_url,
         "published_at": published_at.isoformat().replace("+00:00", "Z") if published_at else None,
-        "latitude": anchor.latitude,
-        "longitude": anchor.longitude,
-        "location_label": anchor.label,
-        "location_inferred": True,
+        "latitude": location_patch["latitude"],
+        "longitude": location_patch["longitude"],
+        "location_label": location_patch["location_label"],
+        "location_source": location_patch["location_source"],
+        "verified": location_patch["verified"],
+        "location_meta": location_patch["location_meta"],
+        "enrichment_status": item.enrichment_status,
+        "enrichment_error": item.enrichment_error,
+        "enriched_at": _serialize_enriched_at(item.enriched_at),
         "is_focus_match": item.feed_region == active_region,
     }
 
@@ -412,6 +1063,7 @@ def _build_payload(
     lon: float | None,
     active_region: str,
     items: list[ParsedNewsItem],
+    cruise_items: list[ParsedNewsItem] | None = None,
     sources: list[NewsFeedSource],
     errors: list[str],
     stale: bool,
@@ -426,10 +1078,15 @@ def _build_payload(
             "lon": lon,
             "region": active_region,
             "label": profile.label,
+            "display_region": get_region_anchor(active_region).label,
             "accent": profile.accent,
         },
         "sources": _serialize_sources(sources),
         "items": [_serialize_item(item, active_region=active_region) for item in items],
+        "cruise_items": [
+            _serialize_item(item, active_region=active_region)
+            for item in (cruise_items if cruise_items is not None else items)
+        ],
         "errors": errors,
         "stale": stale,
     }
@@ -472,6 +1129,68 @@ def _store_region_cache(region: str, *, items: list[ParsedNewsItem], sources: li
     )
 
 
+async def _apply_cached_locations_and_enqueue(items: list[ParsedNewsItem]) -> list[ParsedNewsItem]:
+    if not items:
+        return items
+
+    from app.services.earth_news_queue import (
+        enqueue_target_location_job,
+        get_cached_target_location_patch,
+    )
+
+    async def enqueue_item(item: ParsedNewsItem, *, force: bool = False) -> bool:
+        return await enqueue_target_location_job(build_target_location_job_payload(item), force=force)
+
+    async def apply_location(item: ParsedNewsItem) -> ParsedNewsItem:
+        cached_patch = await get_cached_target_location_patch(item.id)
+        if cached_patch:
+            apply_enrichment_patch_to_item(item, cached_patch)
+            if not _has_default_localization(item):
+                queued = await enqueue_item(item, force=True)
+                if queued and item.enrichment_status in {
+                    "pending",
+                    "unavailable",
+                    "provider_error",
+                    "parse_error",
+                    "no_result",
+                    "location_only",
+                }:
+                    item.enrichment_status = "queued"
+            return item
+
+        queued = await enqueue_item(item)
+        item.location_patch = build_anchor_location_patch(
+            item,
+            queued=queued,
+            queue_available=queued,
+        )
+        return item
+
+    return list(await asyncio.gather(*(apply_location(item) for item in items)))
+
+
+async def _enqueue_unverified_locations(items: list[ParsedNewsItem]) -> None:
+    if not items:
+        return
+
+    from app.services.earth_news_queue import enqueue_target_location_job
+
+    await asyncio.gather(
+        *(
+            enqueue_target_location_job(
+                build_target_location_job_payload(item),
+                force=not _has_default_localization(item),
+            )
+            for item in items
+            if (
+                item.location_patch is None
+                or item.location_patch.get("verified") is False
+                or not _has_default_localization(item)
+            )
+        )
+    )
+
+
 async def _fetch_source(
     client: httpx.AsyncClient,
     source: NewsFeedSource,
@@ -484,11 +1203,10 @@ async def _fetch_source(
         return source, [], str(exc)
 
 
-async def get_earth_news_payload(lat: float | None = None, lon: float | None = None) -> dict[str, Any]:
-    active_region = determine_focus_region(lat, lon)
-    sources = get_sources_for_region(active_region)
+async def _fetch_rss_items_for_sources(
+    sources: list[NewsFeedSource],
+) -> tuple[list[ParsedNewsItem], list[str]]:
     errors: list[str] = []
-
     async with httpx.AsyncClient(
         timeout=REQUEST_TIMEOUT,
         follow_redirects=True,
@@ -502,9 +1220,29 @@ async def get_earth_news_payload(lat: float | None = None, lon: float | None = N
             errors.append(f"{source.name}: {error}")
             continue
         fetched_items.extend(items)
+    return fetched_items, errors
 
+
+def _needs_rss_supplement(*, item_count: int, newest_at: datetime | None) -> bool:
+    if item_count < MAX_ITEMS_TOTAL:
+        return True
+    if newest_at is None:
+        return True
+    age_seconds = (datetime.now(UTC) - newest_at).total_seconds()
+    return age_seconds > RSS_SUPPLEMENT_MAX_AGE_SECONDS
+
+
+async def _get_earth_news_payload_from_rss_only(
+    *,
+    lat: float | None,
+    lon: float | None,
+    active_region: str,
+    sources: list[NewsFeedSource],
+) -> dict[str, Any]:
+    fetched_items, errors = await _fetch_rss_items_for_sources(sources)
     ranked_items = _rank_and_trim_items(fetched_items, active_region=active_region)
     if ranked_items:
+        ranked_items = await _apply_cached_locations_and_enqueue(ranked_items)
         _store_region_cache(active_region, items=ranked_items, sources=sources)
         return _build_payload(
             lat=lat,
@@ -518,6 +1256,7 @@ async def get_earth_news_payload(lat: float | None = None, lon: float | None = N
 
     cached = _get_cached_region_feed(active_region)
     if cached:
+        cached.items = await _apply_cached_locations_and_enqueue(cached.items)
         return _build_payload(
             lat=lat,
             lon=lon,
@@ -538,3 +1277,64 @@ async def get_earth_news_payload(lat: float | None = None, lon: float | None = N
         errors=errors,
         stale=False,
     )
+
+
+async def get_earth_news_payload(
+    lat: float | None = None,
+    lon: float | None = None,
+    *,
+    provider_client: AIProviderClient | None = None,
+    db: AsyncSession | None = None,
+) -> dict[str, Any]:
+    del provider_client
+    active_region = determine_focus_region(lat, lon)
+    sources = get_sources_for_region(active_region)
+
+    if db is None:
+        return await _get_earth_news_payload_from_rss_only(
+            lat=lat,
+            lon=lon,
+            active_region=active_region,
+            sources=sources,
+        )
+
+    from app.services.earth_news_store import (
+        get_earth_news_freshness,
+        list_earth_news_cruise_items,
+        list_earth_news_items,
+        upsert_earth_news_items,
+    )
+
+    errors: list[str] = []
+    item_count, newest_at = await get_earth_news_freshness(db, active_region=active_region)
+    should_supplement = _needs_rss_supplement(item_count=item_count, newest_at=newest_at)
+    if should_supplement:
+        fetched_items, errors = await _fetch_rss_items_for_sources(sources)
+        ranked_fetched_items = _rank_and_trim_items(fetched_items, active_region=active_region)
+        await upsert_earth_news_items(db, ranked_fetched_items)
+
+    items = await list_earth_news_items(
+        db,
+        active_region=active_region,
+        limit=MAX_ITEMS_TOTAL,
+    )
+    if hasattr(db, "execute"):
+        cruise_items = await list_earth_news_cruise_items(
+            db,
+            limit=MAX_ITEMS_TOTAL * len(REGION_ANCHORS),
+        )
+    else:
+        cruise_items = items
+    await _enqueue_unverified_locations(items)
+    stale = bool(errors and items)
+
+    return _build_payload(
+        lat=lat,
+        lon=lon,
+        active_region=active_region,
+        items=items,
+        cruise_items=cruise_items,
+        sources=sources,
+        errors=errors,
+        stale=stale,
+    )

backend/app/services/earth_news_queue.py

@@ -0,0 +1,234 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+import json
+from typing import Any, Protocol
+
+import redis.asyncio as redis
+from redis.exceptions import ResponseError
+
+from app.core.config import settings
+from app.core.logging import get_logger
+
+
+logger = get_logger(__name__, service="earth_news")
+
+TARGET_LOCATION_STREAM = "earth_news:target_location:jobs"
+TARGET_LOCATION_GROUP = "earth_news_target_location"
+TARGET_LOCATION_DEAD_LETTER_STREAM = "earth_news:target_location:dead"
+TARGET_LOCATION_RESULT_TTL_SECONDS = 60 * 60 * 12
+TARGET_LOCATION_JOB_DEDUP_TTL_SECONDS = 60 * 60 * 6
+TARGET_LOCATION_MAX_ATTEMPTS = 3
+
+_redis_client: redis.Redis | None = None
+
+
+@dataclass(frozen=True)
+class NewsTargetLocationMessage:
+    message_id: str
+    item_id: str
+    payload: dict[str, Any]
+    attempts: int = 0
+
+
+class NewsTargetLocationQueue(Protocol):
+    async def enqueue(self, *, item_id: str, payload: dict[str, Any], force: bool = False) -> bool:
+        ...
+
+    async def consume_batch(
+        self,
+        *,
+        consumer_name: str,
+        count: int,
+        block_ms: int,
+    ) -> list[NewsTargetLocationMessage]:
+        ...
+
+    async def ack(self, message_id: str) -> None:
+        ...
+
+    async def retry_or_dead_letter(
+        self,
+        message: NewsTargetLocationMessage,
+        *,
+        error: str,
+    ) -> None:
+        ...
+
+
+def _get_redis_client() -> redis.Redis:
+    global _redis_client
+    if _redis_client is None:
+        _redis_client = redis.from_url(settings.REDIS_URL, decode_responses=True)
+    return _redis_client
+
+
+def _result_key(item_id: str) -> str:
+    return f"earth_news:target_location:result:{item_id}"
+
+
+def _queued_key(item_id: str) -> str:
+    return f"earth_news:target_location:queued:{item_id}"
+
+
+class RedisStreamsNewsTargetLocationQueue:
+    def __init__(self, client: redis.Redis | None = None) -> None:
+        self.client = client or _get_redis_client()
+        self._group_ready = False
+
+    async def _ensure_group(self) -> None:
+        if self._group_ready:
+            return
+        try:
+            await self.client.xgroup_create(
+                TARGET_LOCATION_STREAM,
+                TARGET_LOCATION_GROUP,
+                id="0",
+                mkstream=True,
+            )
+        except ResponseError as exc:
+            if "BUSYGROUP" not in str(exc):
+                raise
+        self._group_ready = True
+
+    async def enqueue(self, *, item_id: str, payload: dict[str, Any], force: bool = False) -> bool:
+        await self._ensure_group()
+        if force:
+            await self.client.delete(_result_key(item_id), _queued_key(item_id))
+        elif await self.client.exists(_result_key(item_id)):
+            return False
+        queued = await self.client.set(
+            _queued_key(item_id),
+            "1",
+            nx=True,
+            ex=TARGET_LOCATION_JOB_DEDUP_TTL_SECONDS,
+        )
+        if not queued:
+            return bool(await self.client.exists(_queued_key(item_id)))
+        await self.client.xadd(
+            TARGET_LOCATION_STREAM,
+            {
+                "item_id": item_id,
+                "attempts": "0",
+                "payload": json.dumps(payload, ensure_ascii=False),
+            },
+        )
+        return True
+
+    async def consume_batch(
+        self,
+        *,
+        consumer_name: str,
+        count: int,
+        block_ms: int,
+    ) -> list[NewsTargetLocationMessage]:
+        await self._ensure_group()
+        streams = await self.client.xreadgroup(
+            TARGET_LOCATION_GROUP,
+            consumer_name,
+            {TARGET_LOCATION_STREAM: ">"},
+            count=count,
+            block=block_ms,
+        )
+        messages: list[NewsTargetLocationMessage] = []
+        for _stream_name, stream_messages in streams:
+            for message_id, fields in stream_messages:
+                raw_payload = fields.get("payload")
+                item_id = fields.get("item_id")
+                if not raw_payload or not item_id:
+                    await self.ack(message_id)
+                    continue
+                try:
+                    payload = json.loads(raw_payload)
+                except json.JSONDecodeError:
+                    await self.ack(message_id)
+                    continue
+                attempts = int(fields.get("attempts") or 0)
+                messages.append(
+                    NewsTargetLocationMessage(
+                        message_id=message_id,
+                        item_id=item_id,
+                        payload=payload,
+                        attempts=attempts,
+                    )
+                )
+        return messages
+
+    async def ack(self, message_id: str) -> None:
+        await self.client.xack(TARGET_LOCATION_STREAM, TARGET_LOCATION_GROUP, message_id)
+
+    async def retry_or_dead_letter(
+        self,
+        message: NewsTargetLocationMessage,
+        *,
+        error: str,
+    ) -> None:
+        await self.ack(message.message_id)
+        if message.attempts + 1 >= TARGET_LOCATION_MAX_ATTEMPTS:
+            await self.client.xadd(
+                TARGET_LOCATION_DEAD_LETTER_STREAM,
+                {
+                    "item_id": message.item_id,
+                    "attempts": str(message.attempts + 1),
+                    "error": error,
+                    "payload": json.dumps(message.payload, ensure_ascii=False),
+                },
+            )
+            return
+        await self.client.xadd(
+            TARGET_LOCATION_STREAM,
+            {
+                "item_id": message.item_id,
+                "attempts": str(message.attempts + 1),
+                "payload": json.dumps(message.payload, ensure_ascii=False),
+            },
+        )
+
+
+def get_news_target_location_queue() -> NewsTargetLocationQueue:
+    return RedisStreamsNewsTargetLocationQueue()
+
+
+async def enqueue_target_location_job(payload: dict[str, Any], *, force: bool = False) -> bool:
+    item_id = str(payload.get("id") or "")
+    if not item_id:
+        return False
+    try:
+        queue = get_news_target_location_queue()
+        return await queue.enqueue(item_id=item_id, payload=payload, force=force)
+    except Exception as exc:
+        logger.warning_event(
+            "Failed to enqueue Earth news target location job",
+            event="earth_news.target_location.enqueue_failed",
+            context={"item_id": item_id, "error": str(exc)},
+        )
+        return False
+
+
+async def get_cached_target_location_patch(item_id: str) -> dict[str, Any] | None:
+    try:
+        raw_value = await _get_redis_client().get(_result_key(item_id))
+    except Exception as exc:
+        logger.warning_event(
+            "Failed to read Earth news target location cache",
+            event="earth_news.target_location.cache_read_failed",
+            context={"item_id": item_id, "error": str(exc)},
+        )
+        return None
+    if not raw_value:
+        return None
+    try:
+        value = json.loads(raw_value)
+    except json.JSONDecodeError:
+        return None
+    return value if isinstance(value, dict) else None
+
+
+async def save_target_location_patch(item_id: str, patch: dict[str, Any]) -> None:
+    client = _get_redis_client()
+    await client.setex(
+        _result_key(item_id),
+        TARGET_LOCATION_RESULT_TTL_SECONDS,
+        json.dumps(patch, ensure_ascii=False),
+    )
+    await client.delete(_queued_key(item_id))

backend/app/services/earth_news_store.py

@@ -0,0 +1,262 @@
+from __future__ import annotations
+
+from datetime import UTC, datetime
+from typing import Any
+
+from sqlalchemy import func, select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.models.earth_news import EarthNewsItem
+from app.services.earth_news import (
+    ParsedNewsItem,
+    apply_enrichment_patch_to_item,
+    build_anchor_location_patch,
+)
+
+
+def _coerce_datetime(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 _location_patch_from_record(record: EarthNewsItem) -> dict[str, Any]:
+    return {
+        "latitude": record.latitude,
+        "longitude": record.longitude,
+        "location_label": record.location_label,
+        "location_source": record.location_source,
+        "verified": record.verified,
+        "location_meta": dict(record.location_meta or {}),
+    }
+
+
+def record_to_parsed_news_item(record: EarthNewsItem) -> ParsedNewsItem:
+    item = ParsedNewsItem(
+        id=record.id,
+        title=record.title,
+        summary=record.summary or "",
+        url=record.url,
+        source=record.source or "",
+        feed_name=record.feed_name or "",
+        feed_region=record.region or "global",
+        homepage_url=record.homepage_url or "",
+        published_at=_coerce_datetime(record.published_at),
+        content_language=record.content_language or "en",
+        localizations=dict(record.localizations or {}),
+        enrichment_status=record.enrichment_status or "pending",
+        enrichment_error=record.enrichment_error,
+        enriched_at=_coerce_datetime(record.enriched_at),
+    )
+    return apply_enrichment_patch_to_item(item, _location_patch_from_record(record))
+
+
+def _query_sort_key(active_region: str):
+    return (
+        EarthNewsItem.region != active_region,
+        EarthNewsItem.published_at.is_(None),
+        EarthNewsItem.published_at.desc().nullslast(),
+        EarthNewsItem.feed_name.asc(),
+    )
+
+
+async def list_earth_news_items(
+    db: AsyncSession,
+    *,
+    active_region: str,
+    limit: int,
+) -> list[ParsedNewsItem]:
+    regions = {"global", active_region}
+    result = await db.execute(
+        select(EarthNewsItem)
+        .where(EarthNewsItem.region.in_(regions))
+        .order_by(*_query_sort_key(active_region))
+        .limit(limit)
+    )
+    return [record_to_parsed_news_item(record) for record in result.scalars().all()]
+
+
+async def list_earth_news_cruise_items(
+    db: AsyncSession,
+    *,
+    limit: int,
+) -> list[ParsedNewsItem]:
+    result = await db.execute(
+        select(EarthNewsItem)
+        .order_by(
+            EarthNewsItem.region.asc(),
+            EarthNewsItem.published_at.desc().nullslast(),
+            EarthNewsItem.last_seen_at.desc(),
+            EarthNewsItem.feed_name.asc(),
+        )
+        .limit(limit)
+    )
+    return [record_to_parsed_news_item(record) for record in result.scalars().all()]
+
+
+async def get_earth_news_freshness(
+    db: AsyncSession,
+    *,
+    active_region: str,
+) -> tuple[int, datetime | None]:
+    regions = {"global", active_region}
+    result = await db.execute(
+        select(
+            func.count(EarthNewsItem.id),
+            func.max(func.coalesce(EarthNewsItem.published_at, EarthNewsItem.last_seen_at)),
+        ).where(EarthNewsItem.region.in_(regions))
+    )
+    count, newest = result.one()
+    item_count = int(count or 0)
+    if item_count == 0:
+        return 0, None
+    return item_count, _coerce_datetime(newest)
+
+
+async def upsert_earth_news_items(db: AsyncSession, items: list[ParsedNewsItem]) -> int:
+    if not items:
+        return 0
+    now = datetime.now(UTC)
+    existing_result = await db.execute(
+        select(EarthNewsItem).where(EarthNewsItem.id.in_([item.id for item in items]))
+    )
+    existing = {record.id: record for record in existing_result.scalars().all()}
+    changed = 0
+    for item in items:
+        record = existing.get(item.id)
+        if record is None:
+            patch = build_anchor_location_patch(item)
+            record = EarthNewsItem(
+                id=item.id,
+                title=item.title,
+                summary=item.summary,
+                content_language=item.content_language,
+                localizations=dict(item.localizations or {}),
+                url=item.url,
+                source=item.source,
+                feed_name=item.feed_name,
+                region=item.feed_region,
+                homepage_url=item.homepage_url,
+                published_at=item.published_at,
+                latitude=patch["latitude"],
+                longitude=patch["longitude"],
+                location_label=patch["location_label"],
+                location_source=patch["location_source"],
+                verified=patch["verified"],
+                location_meta=patch["location_meta"],
+                first_seen_at=now,
+                last_seen_at=now,
+                enrichment_status=item.enrichment_status,
+                enrichment_error=item.enrichment_error,
+                enriched_at=item.enriched_at,
+            )
+            db.add(record)
+            changed += 1
+            continue
+
+        record.title = item.title
+        record.summary = item.summary
+        record.url = item.url
+        record.source = item.source
+        record.feed_name = item.feed_name
+        record.region = item.feed_region
+        record.homepage_url = item.homepage_url
+        record.published_at = item.published_at
+        record.last_seen_at = now
+        if item.localizations:
+            record.content_language = item.content_language
+            record.localizations = dict(item.localizations or {})
+            record.enrichment_status = item.enrichment_status
+            record.enrichment_error = item.enrichment_error
+            record.enriched_at = item.enriched_at
+        changed += 1
+    await db.flush()
+    return changed
+
+
+async def update_earth_news_item_location(
+    db: AsyncSession,
+    *,
+    item_id: str,
+    patch: dict[str, Any],
+) -> bool:
+    record = await db.get(EarthNewsItem, item_id)
+    if record is None:
+        return False
+    record.latitude = float(patch["latitude"])
+    record.longitude = float(patch["longitude"])
+    record.location_label = str(patch["location_label"])
+    record.location_source = str(patch["location_source"])
+    record.verified = bool(patch["verified"])
+    record.location_meta = dict(patch.get("location_meta") or {})
+    record.resolved_at = datetime.now(UTC) if record.verified else None
+    await db.flush()
+    return True
+
+
+async def update_earth_news_item_enrichment(
+    db: AsyncSession,
+    *,
+    item_id: str,
+    patch: dict[str, Any],
+) -> bool:
+    record = await db.get(EarthNewsItem, item_id)
+    if record is None:
+        return False
+    if "latitude" in patch:
+        record.latitude = float(patch["latitude"])
+        record.longitude = float(patch["longitude"])
+        record.location_label = str(patch["location_label"])
+        record.location_source = str(patch["location_source"])
+        record.verified = bool(patch["verified"])
+        record.location_meta = dict(patch.get("location_meta") or {})
+        record.resolved_at = datetime.now(UTC) if record.verified else None
+    if "content_language" in patch:
+        record.content_language = str(patch.get("content_language") or "en")
+    if "localizations" in patch:
+        record.localizations = dict(patch.get("localizations") or {})
+    if "enrichment_status" in patch:
+        record.enrichment_status = str(patch.get("enrichment_status") or "pending")
+    if "enrichment_error" in patch:
+        record.enrichment_error = patch.get("enrichment_error")
+    if patch.get("enriched_at"):
+        try:
+            parsed_enriched_at = datetime.fromisoformat(
+                str(patch["enriched_at"]).replace("Z", "+00:00")
+            )
+        except ValueError:
+            parsed_enriched_at = datetime.now(UTC)
+        record.enriched_at = _coerce_datetime(parsed_enriched_at)
+    elif patch.get("localizations"):
+        record.enriched_at = datetime.now(UTC)
+    await db.flush()
+    return True
+
+
+async def list_unverified_earth_news_items(
+    db: AsyncSession,
+    *,
+    active_region: str,
+    limit: int,
+) -> list[ParsedNewsItem]:
+    regions = {"global", active_region}
+    result = await db.execute(
+        select(EarthNewsItem)
+        .where(EarthNewsItem.region.in_(regions))
+        .where(EarthNewsItem.verified.is_(False))
+        .order_by(*_query_sort_key(active_region))
+        .limit(limit)
+    )
+    return [record_to_parsed_news_item(record) for record in result.scalars().all()]
+
+
+async def list_all_earth_news_records(db: AsyncSession) -> list[EarthNewsItem]:
+    result = await db.execute(
+        select(EarthNewsItem).order_by(
+            EarthNewsItem.published_at.desc().nullslast(),
+            EarthNewsItem.last_seen_at.desc(),
+        )
+    )
+    return list(result.scalars().all())

backend/app/services/earth_news_worker.py

@@ -0,0 +1,142 @@
+from __future__ import annotations
+
+import asyncio
+from contextlib import suppress
+from socket import gethostname
+from typing import Any
+
+from app.core.logging import get_logger
+from app.core.websocket.broadcaster import broadcaster
+from app.db.session import async_session_factory
+from app.services.ai_client import AIProviderClient
+from app.ai_tasks.prompts import get_effective_prompt
+from app.services.earth_news import (
+    NEWS_ENRICH_PROMPT_KEY,
+    _infer_news_enrichment,
+    build_target_location_patch,
+    parsed_news_item_from_job_payload,
+)
+from app.services.earth_news_queue import (
+    NewsTargetLocationMessage,
+    get_news_target_location_queue,
+    save_target_location_patch,
+)
+from app.services.earth_news_store import update_earth_news_item_enrichment as update_earth_news_item_location
+
+
+logger = get_logger(__name__, service="earth_news")
+
+WORKER_BATCH_SIZE = 4
+WORKER_BLOCK_MS = 5000
+WORKER_BACKOFF_SECONDS = 5.0
+
+_worker_task: asyncio.Task | None = None
+
+
+async def _build_provider_client() -> AIProviderClient | None:
+    try:
+        from app.api.v1.settings import get_runtime_ai_provider_config
+
+        async with async_session_factory() as session:
+            runtime_config = await get_runtime_ai_provider_config(session)
+        return AIProviderClient(
+            service_url=runtime_config["service_url"],
+            service_token=runtime_config["service_token"],
+            timeout=runtime_config["timeout_seconds"],
+            retry_attempts=runtime_config["retry_attempts"],
+            llm_config=runtime_config.get("llm_config") or {},
+        )
+    except Exception as exc:
+        logger.warning_event(
+            "Failed to build Earth news AI provider client",
+            event="earth_news.target_location.provider_unavailable",
+            context={"error": str(exc)},
+        )
+        return None
+
+
+async def process_target_location_message(
+    message: NewsTargetLocationMessage,
+    *,
+    provider_client: AIProviderClient | None,
+) -> dict[str, Any]:
+    item = parsed_news_item_from_job_payload(message.payload)
+    async with async_session_factory() as session:
+        prompt = await get_effective_prompt(session, NEWS_ENRICH_PROMPT_KEY)
+    target, localizations = await _infer_news_enrichment(
+        item,
+        provider_client=provider_client,
+        prompt=prompt,
+    )
+    item.target_location = target
+    item.localizations = localizations or item.localizations
+    patch = build_target_location_patch(item, target)
+    await save_target_location_patch(item.id, patch)
+    async with async_session_factory() as session:
+        await update_earth_news_item_location(session, item_id=item.id, patch=patch)
+        await session.commit()
+    await broadcaster.broadcast_custom(
+        "earth_news",
+        {
+            "item_id": item.id,
+            "patch": patch,
+        },
+    )
+    return patch
+
+
+async def _run_target_location_worker() -> None:
+    consumer_name = f"{gethostname()}:{id(asyncio.current_task())}"
+    queue = get_news_target_location_queue()
+    while True:
+        try:
+            messages = await queue.consume_batch(
+                consumer_name=consumer_name,
+                count=WORKER_BATCH_SIZE,
+                block_ms=WORKER_BLOCK_MS,
+            )
+        except asyncio.CancelledError:
+            raise
+        except Exception as exc:
+            logger.warning_event(
+                "Earth news target location worker queue read failed",
+                event="earth_news.target_location.worker_read_failed",
+                context={"error": str(exc)},
+            )
+            await asyncio.sleep(WORKER_BACKOFF_SECONDS)
+            continue
+
+        if not messages:
+            continue
+        provider_client = await _build_provider_client()
+        for message in messages:
+            try:
+                await process_target_location_message(message, provider_client=provider_client)
+                await queue.ack(message.message_id)
+            except asyncio.CancelledError:
+                raise
+            except Exception as exc:
+                logger.warning_event(
+                    "Earth news target location worker job failed",
+                    event="earth_news.target_location.worker_job_failed",
+                    context={"item_id": message.item_id, "error": str(exc)},
+                )
+                with suppress(Exception):
+                    await queue.retry_or_dead_letter(message, error=str(exc))
+
+
+def start_earth_news_target_worker() -> None:
+    global _worker_task
+    if _worker_task is None or _worker_task.done():
+        _worker_task = asyncio.create_task(_run_target_location_worker())
+
+
+async def stop_earth_news_target_worker() -> None:
+    global _worker_task
+    task = _worker_task
+    if task is None:
+        return
+    task.cancel()
+    with suppress(asyncio.CancelledError):
+        await task
+    _worker_task = None

backend/app/services/email.py

@@ -0,0 +1,123 @@
+"""SMTP-backed email sender.
+
+Generic primitive used by registration/verification today, reusable for alert
+digests and other notifications later. Configuration lives in the `smtp` row of
+`system_settings` and is loaded once per send (small surface, no caching layer
+yet to keep behavior obvious after settings changes).
+"""
+
+from __future__ import annotations
+
+from email.message import EmailMessage
+from typing import Literal, Optional
+
+import aiosmtplib
+from sqlalchemy.ext.asyncio import AsyncSession
+
+OtpPurpose = Literal["register", "verify_email", "reset_password"]
+
+
+class EmailError(Exception):
+    code: str = "EMAIL_ERROR"
+
+
+class EmailNotConfiguredError(EmailError):
+    code = "EMAIL_PROVIDER_NOT_CONFIGURED"
+
+
+class EmailSendError(EmailError):
+    code = "EMAIL_SEND_FAILED"
+
+
+async def _load_smtp_config(db: AsyncSession) -> dict:
+    from app.api.v1.settings import get_setting_payload  # local import avoids cycle
+
+    payload = await get_setting_payload(db, "smtp")
+    if not payload.get("host") or not payload.get("from_address"):
+        raise EmailNotConfiguredError("SMTP host/from_address not set")
+    return payload
+
+
+async def send_email(
+    db: AsyncSession,
+    *,
+    to: str,
+    subject: str,
+    text_body: str,
+    html_body: Optional[str] = None,
+    config: Optional[dict] = None,
+) -> None:
+    cfg = config or await _load_smtp_config(db)
+
+    message = EmailMessage()
+    from_name = (cfg.get("from_name") or "").strip()
+    from_address = cfg["from_address"]
+    message["From"] = f"{from_name} <{from_address}>" if from_name else from_address
+    message["To"] = to
+    message["Subject"] = subject
+    message.set_content(text_body)
+    if html_body:
+        message.add_alternative(html_body, subtype="html")
+
+    use_tls = bool(cfg.get("use_tls", True))
+    use_starttls = bool(cfg.get("use_starttls", False))
+    port = int(cfg.get("port") or (465 if use_tls else 587))
+
+    try:
+        await aiosmtplib.send(
+            message,
+            hostname=cfg["host"],
+            port=port,
+            username=cfg.get("username") or None,
+            password=cfg.get("password") or None,
+            use_tls=use_tls and not use_starttls,
+            start_tls=use_starttls,
+            timeout=int(cfg.get("timeout_seconds") or 20),
+        )
+    except aiosmtplib.SMTPException as exc:
+        raise EmailSendError(str(exc)) from exc
+    except OSError as exc:
+        raise EmailSendError(str(exc)) from exc
+
+
+_SUBJECTS: dict[OtpPurpose, str] = {
+    "register": "Confirm your Planet account",
+    "verify_email": "Verify your Planet email",
+    "reset_password": "Reset your Planet password",
+}
+
+_HEADLINES: dict[OtpPurpose, str] = {
+    "register": "Welcome to Planet — confirm your email to activate your account.",
+    "verify_email": "Confirm your new email address to keep your Planet account active.",
+    "reset_password": "Use this code to set a new password for your Planet account.",
+}
+
+
+async def send_verification_email(
+    db: AsyncSession,
+    *,
+    to: str,
+    code: str,
+    purpose: OtpPurpose,
+    config: Optional[dict] = None,
+) -> None:
+    subject = _SUBJECTS[purpose]
+    headline = _HEADLINES[purpose]
+    text_body = (
+        f"{headline}\n\n"
+        f"Your verification code: {code}\n"
+        "This code expires in 10 minutes. If you did not request it, ignore this email.\n"
+    )
+    html_body = (
+        f"<p>{headline}</p>"
+        f"<p style=\"font-size:24px;letter-spacing:4px;font-family:monospace\"><b>{code}</b></p>"
+        "<p>This code expires in 10 minutes. If you did not request it, ignore this email.</p>"
+    )
+    await send_email(
+        db,
+        to=to,
+        subject=subject,
+        text_body=text_body,
+        html_body=html_body,
+        config=config,
+    )

backend/app/services/llm_provider_catalog.py

@@ -7,6 +7,26 @@ from typing import Any
 import httpx
 
 MODELS_DEV_URL = "https://models.dev/api.json"
+OPENCODE_GO_MODELS_URL = "https://opencode.ai/zen/go/v1/models"
+
+OPENCODE_GO_MODEL_PROVIDER_APIS = {
+    "minimax-m2.7": "anthropic-messages",
+    "minimax-m2.5": "anthropic-messages",
+}
+OPENCODE_GO_FALLBACK_MODELS = [
+    "minimax-m2.7",
+    "minimax-m2.5",
+    "kimi-k2.6",
+    "kimi-k2.5",
+    "glm-5.1",
+    "glm-5",
+    "deepseek-v4-pro",
+    "deepseek-v4-flash",
+    "qwen3.6-plus",
+    "qwen3.5-plus",
+    "mimo-v2.5-pro",
+    "mimo-v2.5",
+]
 
 
 FALLBACK_LLM_PROVIDER_PRESETS: dict[str, dict[str, Any]] = {
@@ -80,6 +100,17 @@ FALLBACK_LLM_PROVIDER_PRESETS: dict[str, dict[str, Any]] = {
         "api_key_env": "OPENROUTER_API_KEY",
         "source": "fallback",
     },
+    "opencode-go": {
+        "provider": "opencode-go",
+        "label": "OpenCode Go",
+        "provider_api": "openai-completions",
+        "base_url": "https://opencode.ai/zen/go/v1",
+        "model": "glm-5.1",
+        "models": OPENCODE_GO_FALLBACK_MODELS,
+        "model_provider_apis": OPENCODE_GO_MODEL_PROVIDER_APIS,
+        "api_key_env": "OPENCODE_GO_API_KEY",
+        "source": "fallback",
+    },
     "ollama": {
         "provider": "ollama",
         "label": "Ollama Local",
@@ -114,8 +145,43 @@ def get_fallback_llm_provider_preset(provider: str) -> dict[str, Any]:
     return dict(FALLBACK_LLM_PROVIDER_PRESETS[key])
 
 
-async def refresh_llm_provider_preset(provider: str) -> dict[str, Any]:
+def _opencode_go_model_provider_apis(model_ids: list[str]) -> dict[str, str]:
+    return {
+        model_id: OPENCODE_GO_MODEL_PROVIDER_APIS.get(model_id, "openai-completions")
+        for model_id in model_ids
+    }
+
+
+async def refresh_llm_provider_preset(provider: str, api_key: str | None = None) -> dict[str, Any]:
     fallback = get_fallback_llm_provider_preset(provider)
+    if fallback["provider"] == "opencode-go":
+        headers = {"User-Agent": "Planet/1.0"}
+        if api_key:
+            headers["Authorization"] = f"Bearer {api_key}"
+        async with httpx.AsyncClient(timeout=15.0, follow_redirects=True) as client:
+            response = await client.get(
+                OPENCODE_GO_MODELS_URL,
+                headers=headers,
+            )
+            response.raise_for_status()
+            payload = response.json()
+
+        data = payload.get("data") if isinstance(payload, dict) else []
+        model_ids = [
+            str(item.get("id"))
+            for item in data
+            if isinstance(item, dict) and item.get("id")
+        ][:120]
+        if not model_ids:
+            model_ids = fallback["models"]
+        return {
+            **fallback,
+            "model": fallback["model"] if fallback["model"] in model_ids else model_ids[0],
+            "models": model_ids,
+            "model_provider_apis": _opencode_go_model_provider_apis(model_ids),
+            "source": OPENCODE_GO_MODELS_URL,
+        }
+
     models_dev_key = MODELS_DEV_PROVIDER_KEYS.get(fallback["provider"])
     if not models_dev_key:
         return fallback

backend/app/services/location/models.py

@@ -51,6 +51,7 @@ class LocationCandidate:
     matched_location_name: str | None = None
     location_verified_at: str | None = None
     suggested_registry_entry: dict[str, Any] | None = None
+    raw_payload: dict[str, Any] | None = None
 
     def to_dict(self) -> dict[str, Any]:
         return {
@@ -70,6 +71,7 @@ class LocationCandidate:
             "matched_location_name": self.matched_location_name,
             "location_verified_at": self.location_verified_at,
             "suggested_registry_entry": self.suggested_registry_entry,
+            "raw_payload": self.raw_payload,
         }
 
 

backend/app/services/otp.py

@@ -0,0 +1,100 @@
+"""One-time verification codes backed by Redis.
+
+Reusable primitive for register/verify-email/reset-password (and any future 2FA or
+phone-number verification). Codes are bcrypt-hashed before storage so a Redis dump
+does not leak active codes.
+"""
+
+from __future__ import annotations
+
+import json
+import secrets
+from typing import Literal
+
+import bcrypt
+
+from app.core.security import redis_client
+
+OtpPurpose = Literal["register", "verify_email", "reset_password"]
+
+CODE_TTL_SECONDS = 600  # 10 minutes
+RESEND_COOLDOWN_SECONDS = 60
+MAX_ATTEMPTS = 5
+CODE_LENGTH = 6
+
+
+class OtpError(Exception):
+    code: str = "OTP_ERROR"
+
+
+class OtpResendRateLimited(OtpError):
+    code = "OTP_RESEND_RATE_LIMITED"
+
+    def __init__(self, retry_after_seconds: int) -> None:
+        super().__init__(f"Resend allowed in {retry_after_seconds}s")
+        self.retry_after_seconds = retry_after_seconds
+
+
+class OtpInvalid(OtpError):
+    code = "OTP_INVALID"
+
+
+class OtpExpired(OtpError):
+    code = "OTP_EXPIRED"
+
+
+class OtpAttemptsExceeded(OtpError):
+    code = "OTP_ATTEMPTS_EXCEEDED"
+
+
+def _code_key(email: str, purpose: OtpPurpose) -> str:
+    return f"otp:{purpose}:{email.lower()}"
+
+
+def _rate_key(email: str, purpose: OtpPurpose) -> str:
+    return f"otp_rate:{purpose}:{email.lower()}"
+
+
+def _generate_code() -> str:
+    # secrets.randbelow gives uniform 0..10**CODE_LENGTH-1 without modulo bias
+    return f"{secrets.randbelow(10 ** CODE_LENGTH):0{CODE_LENGTH}d}"
+
+
+def check_resend_allowed(email: str, purpose: OtpPurpose) -> None:
+    ttl = redis_client.ttl(_rate_key(email, purpose))
+    if ttl and ttl > 0:
+        raise OtpResendRateLimited(ttl)
+
+
+def issue_code(email: str, purpose: OtpPurpose) -> str:
+    """Generate a new code, persist its hash, and start the resend cooldown.
+
+    Caller is responsible for delivering the returned plaintext (e.g. via email).
+    Any pre-existing code for the same (purpose, email) is overwritten.
+    """
+    check_resend_allowed(email, purpose)
+    code = _generate_code()
+    hashed = bcrypt.hashpw(code.encode(), bcrypt.gensalt()).decode()
+    payload = json.dumps({"hash": hashed, "attempts": 0})
+    redis_client.set(_code_key(email, purpose), payload, ex=CODE_TTL_SECONDS)
+    redis_client.set(_rate_key(email, purpose), "1", ex=RESEND_COOLDOWN_SECONDS)
+    return code
+
+
+def verify_code(email: str, purpose: OtpPurpose, code: str) -> None:
+    """Validate and consume a code. Raises subclasses of OtpError on failure."""
+    key = _code_key(email, purpose)
+    raw = redis_client.get(key)
+    if raw is None:
+        raise OtpExpired("Code expired or never issued")
+    record = json.loads(raw)
+    attempts = int(record.get("attempts", 0))
+    if attempts >= MAX_ATTEMPTS:
+        redis_client.delete(key)
+        raise OtpAttemptsExceeded("Too many invalid attempts")
+    if not bcrypt.checkpw(code.encode(), record["hash"].encode()):
+        record["attempts"] = attempts + 1
+        ttl = redis_client.ttl(key)
+        redis_client.set(key, json.dumps(record), ex=max(ttl, 1))
+        raise OtpInvalid("Incorrect code")
+    redis_client.delete(key)

backend/app/services/playground_chat_service.py

@@ -10,6 +10,7 @@ from fastapi import HTTPException, status
 from sqlalchemy import func, select, update
 from sqlalchemy.ext.asyncio import AsyncSession
 
+from app.core.logging import get_logger
 from app.db.session import async_session_factory
 from app.models.playground_message import PlaygroundMessage
 from app.models.playground_session import PlaygroundSession
@@ -27,12 +28,15 @@ from app.schemas.ai import (
     SituationalAnalysisRequest,
 )
 from app.services.ai_client import AIProviderClient
+from app.services.business_logs import emit_business_log, exception_context
 from app.services.playground_session_store import _to_response as session_to_response
 from app.services.playground_session_store import upsert_playground_session
 
+logger = get_logger(__name__, service="ai")
 STREAM_CHUNK_SIZE = 24
 STREAM_INTERVAL_SECONDS = 0.08
 THINKING_PREVIEW_SECONDS = 2.6
+ORPHANED_RUN_MESSAGE = "后台生成任务已中断，请点击上一条用户消息的重试按钮重新生成。"
 
 
 class _ActiveRun:
@@ -179,6 +183,7 @@ async def _build_thread_response(
     session: PlaygroundSession,
 ) -> PlaygroundThreadResponse:
     messages = await _list_visible_messages(db, session_id=session.id)
+    messages = await _reconcile_orphaned_active_messages(db, messages)
     id_map = {item.id: item.public_id for item in messages}
     return PlaygroundThreadResponse(
         session=session_to_response(session),
@@ -186,6 +191,30 @@ async def _build_thread_response(
     )
 
 
+async def _reconcile_orphaned_active_messages(
+    db: AsyncSession,
+    messages: list[PlaygroundMessage],
+) -> list[PlaygroundMessage]:
+    changed = False
+    for item in messages:
+        if item.status not in {"pending", "thinking", "answering"}:
+            continue
+        if item.public_id in _ACTIVE_RUNS:
+            continue
+        item.status = "error"
+        item.content = item.content or ORPHANED_RUN_MESSAGE
+        orphan_meta = "错误: 后台任务已中断"
+        if orphan_meta not in (item.meta or []):
+            item.meta = [*(item.meta or []), orphan_meta]
+        changed = True
+    if changed:
+        await db.flush()
+        await db.commit()
+        for item in messages:
+            await db.refresh(item)
+    return messages
+
+
 async def get_thread(
     db: AsyncSession,
     *,
@@ -550,6 +579,15 @@ def _build_conversation_history(messages: Sequence[PlaygroundMessage], current_u
     return history[-8:]
 
 
+def _format_run_exception(exc: Exception) -> str:
+    if isinstance(exc, HTTPException):
+        detail = exc.detail
+        if isinstance(detail, str):
+            return detail
+        return str(detail)
+    return str(exc) or type(exc).__name__
+
+
 async def _run_assistant_message(
     *,
     user_id: int,
@@ -589,7 +627,42 @@ async def _run_assistant_message(
                 thinking={"type": "enabled"},
             )
 
+        await emit_business_log(
+            logger,
+            event="ai.playground.run.start",
+            message="Playground AI run started",
+            category="ai",
+            service="ai",
+            module=__name__,
+            request_id=request_id,
+            user_id=user_id,
+            context={
+                "session_id": session_id,
+                "session_key": session_key,
+                "user_message_id": user_message_id,
+                "assistant_message_id": assistant_message_id,
+                "preset": payload.selected_preset_key,
+            },
+        )
         analysis = await provider_client.analyze(request_payload, request_id=request_id)
+        await emit_business_log(
+            logger,
+            event="ai.playground.run.success",
+            message="Playground AI run completed",
+            category="ai",
+            service="ai",
+            module=__name__,
+            request_id=request_id,
+            user_id=user_id,
+            context={
+                "session_id": session_id,
+                "session_key": session_key,
+                "provider": analysis.provider,
+                "model": analysis.model,
+                "content_block_count": len(analysis.content_blocks or []),
+                "thinking_block_count": len(analysis.thinking_blocks or []),
+            },
+        )
 
         async with async_session_factory() as db:
             assistant_message = await _mark_message_state(
@@ -669,6 +742,23 @@ async def _run_assistant_message(
                 await db.flush()
             await db.commit()
     except asyncio.CancelledError:
+        await emit_business_log(
+            logger,
+            event="ai.playground.run.cancelled",
+            message="Playground AI run cancelled",
+            category="ai",
+            level="warning",
+            service="ai",
+            module=__name__,
+            request_id=request_id,
+            user_id=user_id,
+            context={
+                "session_id": session_id,
+                "session_key": session_key,
+                "assistant_message_id": assistant_message_id,
+                "duration_ms": round((perf_counter() - started_at) * 1000),
+            },
+        )
         async with async_session_factory() as db:
             result = await db.execute(select(PlaygroundMessage).where(PlaygroundMessage.id == assistant_message_id))
             message = result.scalar_one_or_none()
@@ -680,13 +770,38 @@ async def _run_assistant_message(
                 await db.commit()
         raise
     except Exception as exc:
+        await emit_business_log(
+            logger,
+            event="ai.playground.run.failed",
+            message="Playground AI run failed",
+            category="ai",
+            level="error",
+            service="ai",
+            module=__name__,
+            request_id=request_id,
+            user_id=user_id,
+            context=exception_context(
+                exc,
+                {
+                    "session_id": session_id,
+                    "session_key": session_key,
+                    "assistant_message_id": assistant_message_id,
+                    "duration_ms": round((perf_counter() - started_at) * 1000),
+                },
+            ),
+        )
+        error_message = _format_run_exception(exc)
         async with async_session_factory() as db:
             result = await db.execute(select(PlaygroundMessage).where(PlaygroundMessage.id == assistant_message_id))
             message = result.scalar_one_or_none()
             if message is not None:
                 message.status = "error"
-                message.content = message.content or "分析失败，请检查 AI Provider 配置或稍后再试。"
-                message.meta = [*(message.meta or []), f"错误: {type(exc).__name__}"]
+                message.content = message.content or f"分析失败：{error_message}"
+                message.meta = [
+                    *(message.meta or []),
+                    f"Request ID: {request_id}",
+                    f"错误: {error_message}",
+                ]
                 await db.flush()
                 await db.commit()
     finally:

backend/app/services/scheduler.py

@@ -13,6 +13,7 @@ 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.business_logs import emit_business_log, emit_business_log_background, exception_context
 from app.services.collectors.registry import collector_registry
 from app.services.datasource_connectivity import (
     build_builtin_connectivity_checksum,
@@ -124,6 +125,15 @@ async def run_collector_task(collector_name: str):
                 event="collector.run.skipped_disabled",
                 context={"collector_name": collector_name},
             )
+            await emit_business_log(
+                logger,
+                event="collector.run.skipped_disabled",
+                message="Skipping disabled collector",
+                category="collector",
+                service="scheduler",
+                module=__name__,
+                context={"collector_name": collector_name, "datasource_id": datasource.id, "status": "skipped"},
+            )
             return
 
         running_result = await db.execute(
@@ -152,6 +162,21 @@ async def run_collector_task(collector_name: str):
                     event="collector.run.skipped_already_running",
                     context={"collector_name": collector_name, "task_id": existing_running.id},
                 )
+                await emit_business_log(
+                    logger,
+                    event="collector.run.skipped_already_running",
+                    message="Skipping collector trigger because task is already running",
+                    category="collector",
+                    level="warning",
+                    service="scheduler",
+                    module=__name__,
+                    context={
+                        "collector_name": collector_name,
+                        "datasource_id": datasource.id,
+                        "task_id": existing_running.id,
+                        "status": "skipped",
+                    },
+                )
                 return
 
             existing_error = (existing_running.error_message or "").strip()
@@ -173,21 +198,55 @@ async def run_collector_task(collector_name: str):
                 event="collector.run.stale_task_failed",
                 context={"collector_name": collector_name, "task_id": existing_running.id},
             )
+            await emit_business_log(
+                logger,
+                event="collector.run.stale_task_failed",
+                message="Marked stale running task as failed before rerun",
+                category="collector",
+                level="warning",
+                service="scheduler",
+                module=__name__,
+                context={
+                    "collector_name": collector_name,
+                    "datasource_id": datasource.id,
+                    "task_id": existing_running.id,
+                    "status": "failed",
+                },
+            )
 
         try:
-            collector._datasource_id = datasource.id
+            datasource_id = datasource.id
+            datasource_source = datasource.source
+            collector._datasource_id = datasource_id
             logger.info_event(
                 "Running collector",
                 event="collector.run.started",
-                context={"collector_name": collector_name, "datasource_id": datasource.id},
+                context={"collector_name": collector_name, "datasource_id": datasource_id},
+            )
+            await emit_business_log(
+                logger,
+                event="collector.run.scheduled_started",
+                message="Scheduler started collector run",
+                category="collector",
+                service="scheduler",
+                module=__name__,
+                context={"collector_name": collector_name, "datasource_id": datasource_id, "status": "running"},
             )
             task_result = await collector.run(db)
+            datasource = await db.get(DataSource, datasource_id)
+            if datasource is None:
+                logger.error_event(
+                    "Datasource disappeared after collector run",
+                    event="collector.run.datasource_missing_after_run",
+                    context={"collector_name": collector_name, "datasource_id": datasource_id},
+                )
+                return
             datasource.last_run_at = datetime.now(UTC)
             datasource.last_status = task_result.get("status")
             if datasource.last_status == "success":
-                effective_candidate = await get_builtin_effective_candidate(db, datasource.source)
+                effective_candidate = await get_builtin_effective_candidate(db, datasource_source)
                 checksum, _credential_context = await build_builtin_connectivity_checksum(
-                    datasource.source,
+                    datasource_source,
                     effective_candidate["endpoint"],
                     effective_candidate["auth_type"],
                     effective_candidate["headers"],
@@ -196,7 +255,7 @@ async def run_collector_task(collector_name: str):
                 )
                 await save_connectivity_success(
                     db,
-                    datasource.source,
+                    datasource_source,
                     checksum,
                     {"status_code": None},
                     connected_by="collection",
@@ -205,9 +264,25 @@ async def run_collector_task(collector_name: str):
             logger.info_event(
                 "Collector completed",
                 event="collector.run.completed",
-                context={"collector_name": collector_name, "datasource_id": datasource.id, "result": task_result},
+                context={"collector_name": collector_name, "datasource_id": datasource_id, "result": task_result},
+            )
+            await emit_business_log(
+                logger,
+                event="collector.run.scheduled_completed",
+                message="Scheduler completed collector run",
+                category="collector",
+                service="scheduler",
+                module=__name__,
+                context={
+                    "collector_name": collector_name,
+                    "datasource_id": datasource_id,
+                    "status": task_result.get("status"),
+                    "result": task_result,
+                },
             )
         except asyncio.CancelledError:
+            await db.rollback()
+            datasource = await db.get(DataSource, datasource_id)
             datasource.last_run_at = datetime.now(UTC)
             datasource.last_status = "cancelled"
             await db.commit()
@@ -216,8 +291,20 @@ async def run_collector_task(collector_name: str):
                 event="collector.run.cancelled",
                 context={"collector_name": collector_name, "datasource_id": datasource.id},
             )
+            await emit_business_log(
+                logger,
+                event="collector.run.cancelled",
+                message="Collector cancelled by operator",
+                category="collector",
+                level="warning",
+                service="scheduler",
+                module=__name__,
+                context={"collector_name": collector_name, "datasource_id": datasource.id, "status": "cancelled"},
+            )
             raise
         except Exception as exc:
+            await db.rollback()
+            datasource = await db.get(DataSource, datasource_id)
             datasource.last_run_at = datetime.now(UTC)
             datasource.last_status = "failed"
             await db.commit()
@@ -226,6 +313,19 @@ async def run_collector_task(collector_name: str):
                 event="collector.run.failed",
                 context={"collector_name": collector_name, "datasource_id": datasource.id, "error": str(exc)},
             )
+            await emit_business_log(
+                logger,
+                event="collector.run.failed",
+                message="Collector failed",
+                category="collector",
+                level="error",
+                service="scheduler",
+                module=__name__,
+                context=exception_context(
+                    exc,
+                    {"collector_name": collector_name, "datasource_id": datasource.id, "status": "failed"},
+                ),
+            )
 
 
 async def cleanup_stale_running_tasks(max_age_hours: int = 2) -> int:
@@ -347,6 +447,16 @@ def run_collector_now(collector_name: str) -> bool:
             event="collector.trigger.skipped_already_running",
             context={"collector_name": collector_name},
         )
+        emit_business_log_background(
+            logger,
+            event="collector.trigger.skipped_already_running",
+            message="Collector is already running in-memory; skipping duplicate trigger",
+            category="collector",
+            level="warning",
+            service="scheduler",
+            module=__name__,
+            context={"collector_name": collector_name, "status": "skipped"},
+        )
         return False
 
     try:
@@ -364,6 +474,15 @@ def run_collector_now(collector_name: str) -> bool:
             event="collector.trigger.started",
             context={"collector_name": collector_name},
         )
+        emit_business_log_background(
+            logger,
+            event="collector.trigger.started",
+            message="Triggered collector",
+            category="collector",
+            service="scheduler",
+            module=__name__,
+            context={"collector_name": collector_name, "status": "queued"},
+        )
         return True
     except Exception as exc:
         logger.error_event(
@@ -371,9 +490,24 @@ def run_collector_now(collector_name: str) -> bool:
             event="collector.trigger.failed",
             context={"collector_name": collector_name, "error": str(exc)},
         )
+        emit_business_log_background(
+            logger,
+            event="collector.trigger.failed",
+            message="Failed to trigger collector",
+            category="collector",
+            level="error",
+            service="scheduler",
+            module=__name__,
+            context=exception_context(exc, {"collector_name": collector_name, "status": "failed"}),
+        )
         return False
 
 
+def is_collector_running(collector_name: str) -> bool:
+    task = get_running_collector_task(collector_name)
+    return bool(task is not None and not task.done())
+
+
 async def cancel_running_collector_now(collector_name: str) -> bool:
     task = get_running_collector_task(collector_name)
     if task is None or task.done():

backend/app/services/situational_alert_ai_brief.py

@@ -10,8 +10,11 @@ from app.models.alert import Alert, AlertSeverity, AlertStatus
 from app.models.bgp_anomaly import BGPAnomaly
 from app.models.bgp_incident import BGPIncident
 from app.schemas.ai import SituationalAnalysisRequest
+from app.ai_tasks.prompts import get_effective_prompt
 from app.services.bgp_ai_brief_store import get_latest_bgp_brief_record
 
+SITUATIONAL_ALERT_BRIEF_PROMPT_KEY = "alerts.situational.brief"
+
 
 def _format_pairs(pairs: list[tuple[str, int]], empty_text: str = "无") -> str:
     if not pairs:
@@ -96,18 +99,24 @@ async def build_situational_alert_brief_request(
         (str(item[0] or "未命名数据源"), item[1])
         for item in alert_source_result.fetchall()
     ]
+    total_alerts = total_alerts_result.scalar() or 0
+    active_alerts = active_alerts_result.scalar() or 0
+    total_incidents = total_incidents_result.scalar() or 0
+    active_incidents = active_incidents_result.scalar() or 0
+    total_anomalies = total_anomalies_result.scalar() or 0
+    active_anomalies = active_anomalies_result.scalar() or 0
 
     facts = [
         (
-            f"系统告警侧：总告警 {total_alerts_result.scalar() or 0} 条，active {active_alerts_result.scalar() or 0} 条；"
+            f"系统告警侧：总告警 {total_alerts} 条，active {active_alerts} 条；"
             f"活跃告警严重度分布为 {_format_pairs(active_alert_severities)}。"
         ),
         (
-            f"BGP态势侧：累计 incidents {total_incidents_result.scalar() or 0} 条，active incidents {active_incidents_result.scalar() or 0} 条；"
+            f"BGP态势侧：累计 incidents {total_incidents} 条，active incidents {active_incidents} 条；"
             f"活跃 incidents 严重度分布为 {_format_pairs(active_bgp_severities)}。"
         ),
         (
-            f"BGP异常侧：累计 anomalies {total_anomalies_result.scalar() or 0} 条，active anomalies {active_anomalies_result.scalar() or 0} 条；"
+            f"BGP异常侧：累计 anomalies {total_anomalies} 条，active anomalies {active_anomalies} 条；"
             f"活跃 anomaly 类型分布为 {_format_pairs(active_anomaly_types)}。"
         ),
     ]
@@ -147,21 +156,23 @@ async def build_situational_alert_brief_request(
 
     context = {
         "source": "situational-alerts",
-        "active_system_alerts": active_alerts_result.scalar() or 0,
+        "active_system_alerts": active_alerts,
         "active_system_alert_severities": dict(active_alert_severities),
         "top_system_alert_sources": dict(active_alert_sources),
-        "active_bgp_incidents": active_incidents_result.scalar() or 0,
+        "active_bgp_incidents": active_incidents,
         "active_bgp_incident_severities": dict(active_bgp_severities),
-        "active_bgp_anomalies": active_anomalies_result.scalar() or 0,
+        "active_bgp_anomalies": active_anomalies,
         "active_bgp_anomaly_types": dict(active_anomaly_types),
         "bgp_hot_regions": dict(bgp_region_counter.most_common(5)),
         "latest_bgp_brief_id": latest_bgp_brief.id if latest_bgp_brief else None,
         "latest_bgp_brief_generated_at": latest_bgp_brief.generated_at if latest_bgp_brief else None,
     }
+    prompt = await get_effective_prompt(db, SITUATIONAL_ALERT_BRIEF_PROMPT_KEY)
 
     request = SituationalAnalysisRequest(
         title="态势告警 AI 简报",
-        objective="综合系统告警、BGP incidents、BGP anomalies 与近期 BGP AI 简报，生成一份面向值班人员的态势告警简报，指出当前最需要关注的风险域、跨模块联动迹象和优先动作。",
+        objective=prompt.prompt,
+        system_prompt=prompt.system_prompt or None,
         observations=facts,
         constraints=[
             "明确区分事实、推断与建议。",

backend/app/services/system_logs.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import json
+import os
 import re
 import shutil
 import subprocess
@@ -86,6 +87,7 @@ class LogSource:
     status: str = "ok"
     buffer_key: str | None = None
     container_name: str | None = None
+    fallback_locations: tuple[str, ...] = ()
 
 
 @dataclass
@@ -104,22 +106,38 @@ class DailyLogMarker:
     dominant_level: str
 
 
+def _planet_state_dir() -> Path:
+    configured = os.getenv("PLANET_STATE_DIR")
+    if configured:
+        return Path(configured).expanduser()
+    xdg_state = os.getenv("XDG_STATE_HOME")
+    if xdg_state:
+        return Path(xdg_state).expanduser() / "planet"
+    return Path.home() / ".local" / "state" / "planet"
+
+
+def _state_log_path(filename: str) -> str:
+    return str(_planet_state_dir() / filename)
+
+
 LOG_SOURCES: dict[str, LogSource] = {
     "backend": LogSource(
         source_id="backend",
         name="后端服务",
         kind="file",
-        location="/tmp/planet_backend.log",
+        location=_state_log_path("backend.log"),
         description="FastAPI 后端、调度器和采集任务共享日志。",
         category="service",
+        fallback_locations=("/tmp/planet_backend.log",),
     ),
     "frontend": LogSource(
         source_id="frontend",
         name="前端开发服务",
         kind="file",
-        location="/tmp/planet_frontend.log",
+        location=_state_log_path("frontend.log"),
         description="控制台与 Earth 前端开发服务输出。",
         category="service",
+        fallback_locations=("/tmp/planet_frontend.log",),
     ),
     "ai-provider": LogSource(
         source_id="ai-provider",
@@ -164,9 +182,18 @@ def normalize_log_levels(level: str | None = None, levels: str | None = None) ->
     return tuple(normalized_levels)
 
 
+def resolve_file_log_path(source: LogSource) -> Path:
+    primary = Path(source.location).expanduser()
+    candidates = (primary, *(Path(item).expanduser() for item in source.fallback_locations))
+    for candidate in candidates:
+        if candidate.exists():
+            return candidate
+    return primary
+
+
 def get_source_status(source: LogSource) -> str:
     if source.kind == "file":
-        path = Path(source.location)
+        path = resolve_file_log_path(source)
         if not path.exists():
             return "missing"
         return "ok" if path.stat().st_size > 0 else "empty"
@@ -190,7 +217,7 @@ def list_log_sources() -> list[dict[str, str]]:
                 "source_id": source.source_id,
                 "name": source.name,
                 "kind": source.kind,
-                "location": source.location,
+                "location": str(resolve_file_log_path(source)) if source.kind == "file" else source.location,
                 "description": source.description,
                 "category": source.category,
                 "status": get_source_status(source),
@@ -339,7 +366,7 @@ def build_buffer_entry(payload: dict[str, Any]) -> StructuredLogEntry:
 
 
 def read_file_entries(source: LogSource, scan_limit: int) -> list[StructuredLogEntry]:
-    path = Path(source.location)
+    path = resolve_file_log_path(source)
     if not path.exists():
         return []
     with path.open("r", encoding="utf-8", errors="replace") as handle:
@@ -511,7 +538,7 @@ def read_log_snapshot(
         "source_id": source.source_id,
         "name": source.name,
         "kind": source.kind,
-        "location": source.location,
+        "location": str(resolve_file_log_path(source)) if source.kind == "file" else source.location,
         "description": source.description,
         "category": source.category,
         "status": get_source_status(source),

backend/app/services/tv_streams.py

@@ -385,13 +385,18 @@ def build_public_tv_payload(
     settings_payload: dict[str, Any],
     collected_sources: list[dict[str, Any]],
 ) -> dict[str, Any]:
+    configured_by_id = {
+        source["id"]: source
+        for source in settings_payload["sources"]
+        if source.get("id")
+    }
     configured_sources = [
         source for source in settings_payload["sources"] if source["is_enabled"]
     ]
 
     merged_by_id = {source["id"]: source for source in configured_sources}
     for source in collected_sources:
-        if source["id"] in merged_by_id or not source["is_enabled"]:
+        if source["id"] in configured_by_id or not source["is_enabled"]:
             continue
         merged_by_id[source["id"]] = source
 

backend/app/services/vessel_ais_aggregation.py

@@ -6,6 +6,7 @@ import json
 from typing import Any, Iterable
 
 from sqlalchemy import select
+from sqlalchemy import Float
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.models.vessel import AISConflictRecord, AISRawObservation, AISSourceHealth
@@ -17,6 +18,10 @@ from app.services.vessel_types import normalize_vessel_type_name
 
 VESSEL_AIS_SCHEMA = "vessel_ais"
 DEFAULT_AGGREGATION_WINDOW_HOURS = 24
+DEFAULT_SNAPSHOT_WINDOW_MINUTES = 60
+MAX_SNAPSHOT_LIMIT = 5000
+MAX_SNAPSHOT_CANDIDATE_MULTIPLIER = 20
+MAX_SNAPSHOT_CANDIDATE_OBSERVATIONS = 100_000
 BARENTSWATCH_DELIVERY_MODE = "polling"
 BARENTSWATCH_TRANSPORT = "http"
 AISSTREAM_DELIVERY_MODE = "realtime_stream"
@@ -564,6 +569,46 @@ async def get_aggregated_vessels(
     return vessels
 
 
+async def get_aggregated_vessels_snapshot(
+    db: AsyncSession,
+    *,
+    bbox: tuple[float, float, float, float],
+    limit: int = 1000,
+    observed_since: datetime | None = None,
+) -> list[dict[str, Any]]:
+    """Return a bounded viewport snapshot without loading the global AIS window."""
+
+    observed_since = observed_since or (
+        datetime.now(UTC) - timedelta(minutes=DEFAULT_SNAPSHOT_WINDOW_MINUTES)
+    )
+    safe_limit = min(max(int(limit or 1000), 1), MAX_SNAPSHOT_LIMIT)
+    candidate_limit = min(
+        max(safe_limit * MAX_SNAPSHOT_CANDIDATE_MULTIPLIER, safe_limit),
+        MAX_SNAPSHOT_CANDIDATE_OBSERVATIONS,
+    )
+    lon_min, lat_min, lon_max, lat_max = bbox
+    payload_lon = AISRawObservation.normalized_payload["lon"].as_string().cast(Float)
+    payload_lat = AISRawObservation.normalized_payload["lat"].as_string().cast(Float)
+
+    stmt = (
+        select(AISRawObservation)
+        .where(AISRawObservation.target_schema == VESSEL_AIS_SCHEMA)
+        .where(AISRawObservation.observed_at >= observed_since)
+        .where(payload_lon >= lon_min)
+        .where(payload_lon <= lon_max)
+        .where(payload_lat >= lat_min)
+        .where(payload_lat <= lat_max)
+        .order_by(AISRawObservation.observed_at.desc(), AISRawObservation.id.desc())
+        .limit(candidate_limit)
+    )
+
+    result = await db.execute(stmt)
+    if not hasattr(result, "scalars"):
+        return []
+    vessels = await aggregate_vessel_observations(db, result.scalars().all())
+    return vessels[:safe_limit]
+
+
 async def get_aggregated_vessel(db: AsyncSession, mmsi: int) -> dict[str, Any] | None:
     observations = await get_vessel_raw_observations(db, mmsi, limit=1000)
     vessels = await aggregate_vessel_observations(db, observations)

backend/scripts/create_admin.py

@@ -17,14 +17,15 @@ async def create_admin():
         existing_user = result.scalar_one_or_none()
 
         if existing_user:
-            print(f"用户 linkong 已存在，更新密码...")
+            print("用户 linkong 已存在，更新密码...")
             existing_user.set_password("LK12345678")
             existing_user.role = "super_admin"
+            existing_user.email = "linkong@planet.local"
         else:
             print("创建管理员用户...")
             user = User(
                 username="linkong",
-                email="linkong@example.com",
+                email="linkong@planet.local",
                 password_hash=get_password_hash("LK12345678"),
                 role="super_admin",
                 is_active=True,

backend/scripts/init_admin.py

@@ -6,29 +6,58 @@ import sys
 sys.path.insert(0, ".")
 
 from app.core.security import get_password_hash
-from app.db.session import engine, async_session_factory
+from app.db.session import async_session_factory
 from app.models.user import User
 
+DEFAULT_LOGIN_USERS = (
+    {
+        "username": "admin",
+        "email": "admin@planet.local",
+        "password": "admin123",
+        "role": "super_admin",
+    },
+    {
+        "username": "linkong",
+        "email": "linkong@planet.local",
+        "password": "LK12345678",
+        "role": "super_admin",
+    },
+)
+
 
 async def create_admin():
     from sqlalchemy import text
 
     async with async_session_factory() as session:
-        result = await session.execute(text("SELECT id FROM users WHERE username = 'admin'"))
-        if result.fetchone():
-            print("Admin user already exists")
+        created = []
+        for default_user in DEFAULT_LOGIN_USERS:
+            result = await session.execute(
+                text("SELECT id FROM users WHERE username = :username"),
+                {"username": default_user["username"]},
+            )
+            if result.fetchone():
+                continue
+
+            session.add(
+                User(
+                    username=default_user["username"],
+                    email=default_user["email"],
+                    password_hash=get_password_hash(default_user["password"]),
+                    role=default_user["role"],
+                    is_active=True,
+                )
+            )
+            created.append(default_user)
+
+        await session.commit()
+        if not created:
+            print("Default login users already exist")
             return
 
-        admin = User(
-            username="admin",
-            email="admin@planet.local",
-            password_hash=get_password_hash("admin123"),
-            role="super_admin",
-            is_active=True,
-        )
-        session.add(admin)
-        await session.commit()
-        print("Admin user created: admin / admin123")
+        for default_user in created:
+            print(
+                f"Default login user created: {default_user['username']} / {default_user['password']}"
+            )
 
 
 if __name__ == "__main__":

backend/scripts/init_db.py

@@ -12,8 +12,20 @@ from sqlalchemy.orm import sessionmaker
 import bcrypt
 
 
-# Generate proper bcrypt hash
-ADMIN_PASSWORD_HASH = bcrypt.hashpw("admin123".encode(), bcrypt.gensalt()).decode()
+DEFAULT_LOGIN_USERS = (
+    {
+        "username": "admin",
+        "email": "admin@planet.local",
+        "password": "admin123",
+        "role": "super_admin",
+    },
+    {
+        "username": "linkong",
+        "email": "linkong@planet.local",
+        "password": "LK12345678",
+        "role": "super_admin",
+    },
+)
 
 
 async def create_admin():
@@ -22,23 +34,42 @@ async def create_admin():
     async_session = sessionmaker(engine, class_=AsyncSession, expire_on_commit=False)
 
     async with async_session() as session:
-        result = await session.execute(
-            text("SELECT id FROM users WHERE username = 'admin'")
-        )
-        if result.fetchone():
-            print("Admin user already exists")
+        created = []
+        for default_user in DEFAULT_LOGIN_USERS:
+            result = await session.execute(
+                text("SELECT id FROM users WHERE username = :username"),
+                {"username": default_user["username"]},
+            )
+            if result.fetchone():
+                continue
+
+            password_hash = bcrypt.hashpw(
+                default_user["password"].encode(), bcrypt.gensalt()
+            ).decode()
+            await session.execute(
+                text("""
+                    INSERT INTO users (username, email, password_hash, role, is_active, created_at, updated_at)
+                    VALUES (:username, :email, :password, :role, true, NOW(), NOW())
+                """),
+                {
+                    "username": default_user["username"],
+                    "email": default_user["email"],
+                    "password": password_hash,
+                    "role": default_user["role"],
+                },
+            )
+            created.append((default_user, password_hash))
+
+        await session.commit()
+        if not created:
+            print("Default login users already exist")
             return
 
-        await session.execute(
-            text("""
-                INSERT INTO users (username, email, password_hash, role, is_active, created_at, updated_at)
-                VALUES ('admin', 'admin@planet.local', :password, 'super_admin', true, NOW(), NOW())
-            """),
-            {"password": ADMIN_PASSWORD_HASH},
-        )
-        await session.commit()
-        print(f"Admin user created: admin / admin123")
-        print(f"Hash: {ADMIN_PASSWORD_HASH}")
+        for default_user, password_hash in created:
+            print(
+                f"Default login user created: {default_user['username']} / {default_user['password']}"
+            )
+            print(f"Hash: {password_hash}")
 
 
 if __name__ == "__main__":

backend/tests/test_ai_observability.py

@@ -0,0 +1,128 @@
+import pytest
+from fastapi import HTTPException
+
+from app.schemas.ai import SituationalAnalysisRequest
+from app.services.ai_tools import web_search as web_search_module
+from app.services.ai_tools.schemas import SearchEvidence, WebSearchConfig, WebSearchProviderConfig
+from app.services.ai_tools.web_search import WebSearchClient
+from app.services import ai_client as ai_client_module
+from app.services.ai_client import AIProviderClient
+
+
+@pytest.mark.asyncio
+async def test_ai_client_analyze_logs_summary_without_prompt(monkeypatch):
+    events = []
+
+    async def fake_emit_business_log(_logger, **payload):
+        events.append(payload)
+
+    async def fake_request(self, method, path, json=None, request_id=None, operation="request", payload_summary=None):
+        return {
+            "provider": "test-provider",
+            "model": "test-model",
+            "content": "ok",
+            "content_blocks": [],
+            "text_blocks": ["ok"],
+            "thinking_blocks": [],
+            "raw_response": {},
+        }
+
+    monkeypatch.setattr(ai_client_module, "emit_business_log", fake_emit_business_log)
+    monkeypatch.setattr(AIProviderClient, "_request", fake_request)
+
+    client = AIProviderClient(
+        service_url="http://provider.test",
+        llm_config={"provider": "openai", "provider_api": "openai-completions", "model": "gpt-test", "api_key": "sk-secret"},
+    )
+    result = await client.analyze(
+        SituationalAnalysisRequest(
+            title="Sensitive title",
+            objective="Do not store this full prompt",
+            observations=["secret observation"],
+            constraints=["secret constraint"],
+            context={"source": "test", "private": "value"},
+        ),
+        request_id="req-ai-test",
+    )
+
+    assert result.model == "test-model"
+    assert [event["event"] for event in events] == [
+        "ai.provider.analyze.start",
+        "ai.provider.analyze.success",
+    ]
+    serialized = str(events)
+    assert "Do not store this full prompt" not in serialized
+    assert "secret observation" not in serialized
+    assert "sk-secret" not in serialized
+    start_context = events[0]["context"]
+    assert start_context["model"] == "gpt-test"
+    assert start_context["input_summary"]["objective_length"] == len("Do not store this full prompt")
+    assert start_context["input_summary"]["observation_count"] == 1
+    assert start_context["input_summary"]["context_keys"] == ["private", "source"]
+
+
+@pytest.mark.asyncio
+async def test_ai_client_analyze_logs_failure(monkeypatch):
+    events = []
+
+    async def fake_emit_business_log(_logger, **payload):
+        events.append(payload)
+
+    async def fake_request(self, method, path, json=None, request_id=None, operation="request", payload_summary=None):
+        raise HTTPException(status_code=502, detail="provider failed")
+
+    monkeypatch.setattr(ai_client_module, "emit_business_log", fake_emit_business_log)
+    monkeypatch.setattr(AIProviderClient, "_request", fake_request)
+
+    client = AIProviderClient(service_url="http://provider.test", llm_config={"provider": "openai", "model": "gpt-test"})
+
+    with pytest.raises(HTTPException):
+        await client.analyze(
+            SituationalAnalysisRequest(title="T", objective="O", observations=["one"]),
+            request_id="req-ai-fail",
+        )
+
+    assert events[-1]["event"] == "ai.provider.analyze.failed"
+    assert events[-1]["level"] == "error"
+    assert events[-1]["context"]["error_type"] == "HTTPException"
+
+
+@pytest.mark.asyncio
+async def test_web_search_logs_query_hash_without_query(monkeypatch):
+    events = []
+
+    async def fake_emit_business_log(_logger, **payload):
+        events.append(payload)
+
+    async def fake_search_tavily(self, config, query, max_results, domains, freshness_days):
+        return [
+            SearchEvidence(
+                title="Example",
+                url="https://example.test",
+                snippet="result",
+                source_provider="tavily",
+            )
+        ]
+
+    monkeypatch.setattr(web_search_module, "emit_business_log", fake_emit_business_log)
+    monkeypatch.setattr(WebSearchClient, "_search_tavily", fake_search_tavily)
+
+    client = WebSearchClient(
+        WebSearchConfig(
+            enabled=True,
+            default_provider="tavily",
+            providers={"tavily": WebSearchProviderConfig(provider="tavily", api_key="secret-key")},
+        )
+    )
+    results = await client.search("secret query text", max_results=1)
+
+    assert len(results) == 1
+    assert [event["event"] for event in events] == [
+        "ai_tool.web_search.start",
+        "ai_tool.web_search.success",
+    ]
+    serialized = str(events)
+    assert "secret query text" not in serialized
+    assert "secret-key" not in serialized
+    assert events[0]["context"]["query_length"] == len("secret query text")
+    assert events[1]["context"]["result_count"] == 1

backend/tests/test_api.py

@@ -5,10 +5,12 @@ from datetime import datetime
 from unittest.mock import patch, AsyncMock
 from httpx import AsyncClient, ASGITransport
 
+from app.api.v1 import earth as earth_api
 from app.main import app
 from app.core.config import settings
 from app.core.security import create_access_token
 from app.db.session import get_db
+from app.models.system_setting import SystemSetting
 from app.models.user import User
 from app.schemas.ai import (
     AIProviderStatusResponse,
@@ -18,6 +20,17 @@ from app.schemas.ai import (
 )
 
 
+class _FakeRedisClient:
+    def sismember(self, *_args, **_kwargs):
+        return False
+
+
+@pytest.fixture(autouse=True)
+def fake_token_blacklist(monkeypatch):
+    """Keep API auth tests independent from an external Redis service."""
+    monkeypatch.setattr("app.core.security.redis_client", _FakeRedisClient())
+
+
 @pytest.fixture
 def auth_headers():
     """Create authentication headers"""
@@ -50,6 +63,148 @@ async def test_root_endpoint():
     assert data["version"] == settings.VERSION
 
 
+class _ScalarOneOrNoneResult:
+    def __init__(self, value=None):
+        self._value = value
+
+    def scalar_one_or_none(self):
+        return self._value
+
+
+class _FakeEarthBrandSession:
+    def __init__(self, record=None):
+        self.record = record
+        self.added = None
+        self.deleted = False
+        self.committed = False
+
+    async def execute(self, statement):
+        if statement.__class__.__name__ == "Delete":
+            self.deleted = True
+            self.record = None
+            return _ScalarOneOrNoneResult(None)
+        return _ScalarOneOrNoneResult(self.record)
+
+    def add(self, record):
+        self.added = record
+        self.record = record
+
+    async def commit(self):
+        self.committed = True
+
+    async def refresh(self, _record):
+        return None
+
+
+def _override_admin_user():
+    return User(id=1, username="testuser", email="test@example.com", role="admin", is_active=True)
+
+
+@pytest.mark.asyncio
+async def test_get_earth_brand_returns_static_defaults():
+    async def override_get_db():
+        yield _FakeEarthBrandSession()
+
+    app.dependency_overrides[get_db] = override_get_db
+    try:
+        transport = ASGITransport(app=app)
+        async with AsyncClient(transport=transport, base_url="http://test") as client:
+            response = await client.get("/api/v1/earth/brand")
+        assert response.status_code == 200
+        data = response.json()
+        assert data["is_default"] is True
+        assert data["brand"]["logo_src"] == "/earth/assets/brand/earth-logo.png"
+        assert data["brand"]["title_src"] == "/earth/assets/brand/title-zh.png"
+    finally:
+        app.dependency_overrides.clear()
+
+
+@pytest.mark.asyncio
+async def test_update_and_reset_earth_brand(auth_headers):
+    session = _FakeEarthBrandSession()
+
+    async def override_get_db():
+        yield session
+
+    app.dependency_overrides.update(
+        {
+            __import__("app.core.security", fromlist=["get_current_user"]).get_current_user: _override_admin_user,
+            get_db: override_get_db,
+        }
+    )
+    try:
+        transport = ASGITransport(app=app)
+        async with AsyncClient(transport=transport, base_url="http://test") as client:
+            update_response = await client.put(
+                "/api/v1/earth/brand",
+                headers=auth_headers,
+                json={
+                    "logo_src": "/earth-brand-assets/custom.png",
+                    "title_src": "",
+                    "title_text": "Custom Earth",
+                    "subtitle": "Custom subtitle",
+                    "description": "Custom description",
+                    "aria_label": "",
+                    "title_alt": "",
+                },
+            )
+            reset_response = await client.delete("/api/v1/earth/brand", headers=auth_headers)
+
+        assert update_response.status_code == 200
+        updated = update_response.json()
+        assert updated["is_default"] is False
+        assert updated["brand"]["title_text"] == "Custom Earth"
+        assert updated["brand"]["aria_label"] == "Custom Earth"
+        assert isinstance(session.added, SystemSetting)
+        assert reset_response.status_code == 200
+        reset = reset_response.json()
+        assert reset["is_default"] is True
+        assert reset["brand"]["logo_src"] == "/earth/assets/brand/earth-logo.png"
+    finally:
+        app.dependency_overrides.clear()
+
+
+@pytest.mark.asyncio
+async def test_upload_earth_brand_asset_rejects_invalid_type(auth_headers):
+    app.dependency_overrides[
+        __import__("app.core.security", fromlist=["get_current_user"]).get_current_user
+    ] = _override_admin_user
+    try:
+        transport = ASGITransport(app=app)
+        async with AsyncClient(transport=transport, base_url="http://test") as client:
+            response = await client.post(
+                "/api/v1/earth/brand/assets",
+                headers=auth_headers,
+                files={"file": ("brand.txt", b"nope", "text/plain")},
+            )
+        assert response.status_code == 400
+        assert response.json()["detail"]["code"] == "unsupported_file_type"
+    finally:
+        app.dependency_overrides.clear()
+
+
+@pytest.mark.asyncio
+async def test_upload_earth_brand_asset_saves_file(auth_headers, tmp_path, monkeypatch):
+    monkeypatch.setattr(earth_api, "EARTH_BRAND_ASSET_DIR", tmp_path)
+    app.dependency_overrides[
+        __import__("app.core.security", fromlist=["get_current_user"]).get_current_user
+    ] = _override_admin_user
+    try:
+        transport = ASGITransport(app=app)
+        async with AsyncClient(transport=transport, base_url="http://test") as client:
+            response = await client.post(
+                "/api/v1/earth/brand/assets",
+                headers=auth_headers,
+                files={"file": ("brand.png", b"png-bytes", "image/png")},
+            )
+        assert response.status_code == 200
+        data = response.json()
+        assert data["url"].startswith("/earth-brand-assets/")
+        assert (tmp_path / data["filename"]).read_bytes() == b"png-bytes"
+    finally:
+        app.dependency_overrides.clear()
+
+
 @pytest.mark.asyncio
 async def test_dashboard_stats_without_auth():
     """Test dashboard stats requires authentication"""
@@ -62,20 +217,43 @@ async def test_dashboard_stats_without_auth():
 @pytest.mark.asyncio
 async def test_dashboard_stats_with_auth(auth_headers):
     """Test dashboard stats with authentication"""
-    with patch("app.api.v1.dashboard.cache.get", return_value=None):
-        with patch("app.api.v1.dashboard.cache.set", return_value=True):
-            with patch("app.db.session.get_db") as mock_get_db:
-                mock_session = AsyncMock()
-                mock_result = AsyncMock()
-                mock_result.scalar.return_value = 0
-                mock_result.fetchall.return_value = []
-                mock_session.execute.return_value = mock_result
+    class _StatsResult:
+        def __init__(self, row):
+            self._row = row
 
-                async def mock_db_context():
-                    yield mock_session
+        def one(self):
+            return self._row
 
-                mock_get_db.return_value = mock_db_context()
+    class _FakeStatsSession:
+        def __init__(self):
+            self._rows = [
+                type("DatasourceStats", (), {"custom_count": 0, "custom_active": 0})(),
+                type("TaskStats", (), {"tasks_today": 0, "success_tasks": 0})(),
+                type(
+                    "AlertStats",
+                    (),
+                    {"critical_alerts": 0, "warning_alerts": 0, "info_alerts": 0},
+                )(),
+            ]
 
+        async def execute(self, _query):
+            return _StatsResult(self._rows.pop(0))
+
+    def override_get_current_user():
+        return User(id=1, username="testuser", email="test@example.com", role="admin", is_active=True)
+
+    async def override_get_db():
+        yield _FakeStatsSession()
+
+    app.dependency_overrides.update(
+        {
+            __import__("app.core.security", fromlist=["get_current_user"]).get_current_user: override_get_current_user,
+            get_db: override_get_db,
+        }
+    )
+    try:
+        with patch("app.api.v1.dashboard.cache.get", return_value=None):
+            with patch("app.api.v1.dashboard.cache.set", return_value=True):
                 transport = ASGITransport(app=app)
                 async with AsyncClient(transport=transport, base_url="http://test") as client:
                     response = await client.get(
@@ -85,6 +263,8 @@ async def test_dashboard_stats_with_auth(auth_headers):
                 assert response.status_code == 200
                 data = response.json()
                 assert "total_datasources" in data
+    finally:
+        app.dependency_overrides.clear()
 
 
 @pytest.mark.asyncio
@@ -492,6 +672,77 @@ async def test_ingest_earth_client_log_accepts_public_events():
         app.dependency_overrides.clear()
 
 
+@pytest.mark.asyncio
+async def test_earth_layer_cache_status_requires_super_admin(auth_headers, monkeypatch):
+    def override_get_current_user():
+        return User(
+            id=1,
+            username="root",
+            email="root@example.com",
+            password_hash="hashed",
+            role="super_admin",
+            is_active=True,
+        )
+
+    monkeypatch.setattr(
+        "app.api.v1.system_control.earth_layer_cache.status",
+        lambda: {
+            "prefix": "earth:layer:v1",
+            "key_count": 2,
+            "memory_bytes": 42,
+            "layers": {"cables": {"keys": 2, "stale_keys": 1, "memory_bytes": 42}},
+        },
+    )
+
+    app.dependency_overrides = {
+        __import__("app.core.security", fromlist=["get_current_user"]).get_current_user: override_get_current_user,
+    }
+    transport = ASGITransport(app=app)
+    try:
+        async with AsyncClient(transport=transport, base_url="http://test") as client:
+            response = await client.get("/api/v1/system/cache/earth-layers", headers=auth_headers)
+        assert response.status_code == 200
+        data = response.json()
+        assert data["prefix"] == "earth:layer:v1"
+        assert data["layers"]["cables"]["stale_keys"] == 1
+    finally:
+        app.dependency_overrides.clear()
+
+
+@pytest.mark.asyncio
+async def test_clear_earth_layer_cache_deletes_only_earth_layer_prefix(auth_headers, monkeypatch):
+    def override_get_current_user():
+        return User(
+            id=1,
+            username="root",
+            email="root@example.com",
+            password_hash="hashed",
+            role="super_admin",
+            is_active=True,
+        )
+
+    captured = {}
+
+    def fake_delete_pattern(pattern="earth:layer:v1:*"):
+        captured["pattern"] = pattern
+        return 3
+
+    monkeypatch.setattr("app.api.v1.system_control.earth_layer_cache.delete_pattern", fake_delete_pattern)
+
+    app.dependency_overrides = {
+        __import__("app.core.security", fromlist=["get_current_user"]).get_current_user: override_get_current_user,
+    }
+    transport = ASGITransport(app=app)
+    try:
+        async with AsyncClient(transport=transport, base_url="http://test") as client:
+            response = await client.delete("/api/v1/system/cache/earth-layers", headers=auth_headers)
+        assert response.status_code == 200
+        assert response.json()["deleted"] == 3
+        assert captured["pattern"] == "earth:layer:v1:*"
+    finally:
+        app.dependency_overrides.clear()
+
+
 @pytest.mark.asyncio
 async def test_request_id_header_is_echoed_when_provided():
     transport = ASGITransport(app=app)

backend/tests/test_bgp_collector_locations.py

@@ -2,9 +2,13 @@
 
 from __future__ import annotations
 
+from unittest.mock import AsyncMock
+
 import pytest
 
+from app.api.v1 import bgp as bgp_api
 from app.services import bgp_collector_locations
+from app.services.location.llm_fallback import LocationLLMFallbackResult
 from app.services.bgp_collector_locations import (
     RIPE_RIS_COLLECTOR_COORDS,
     collect_bgp_collector_location_candidates,
@@ -106,6 +110,75 @@ def test_collect_bgp_collector_candidates_uses_nominatim_when_registry_misses(mo
     assert online[0].needs_confirmation is True
 
 
+@pytest.mark.asyncio
+async def test_collect_bgp_collector_location_uses_llm_when_candidates_empty(monkeypatch):
+    llm_candidate = bgp_collector_locations.LocationCandidate(
+        latitude=45.764,
+        longitude=4.8357,
+        display_name="Lyon, France",
+        precision="city",
+        confidence=0.74,
+        query="llm_factcheck:bgp_collector:rrc-mystery",
+        source="llm_location_factcheck",
+        source_note="LLM location factcheck fallback",
+        matched_fields=("collector",),
+        needs_confirmation=True,
+        city="Lyon",
+        country="France",
+    )
+    monkeypatch.setattr(
+        bgp_api,
+        "get_bgp_collector_location_dict",
+        lambda _collector: {},
+    )
+    monkeypatch.setattr(
+        bgp_api,
+        "collect_bgp_collector_location_candidates",
+        lambda **_kwargs: ([], ["Lyon, France"]),
+    )
+
+    from app.services.location.llm_fallback import LocationSearchEvidenceResult
+
+    async def _search_evidence(**_kwargs):
+        return LocationSearchEvidenceResult(
+            evidence=[
+                {
+                    "title": "RRC source",
+                    "url": "https://example.test/rrc",
+                    "snippet": "rrc-mystery is in Lyon.",
+                }
+            ],
+            attempted_queries=["web_search:bgp_collector:rrc-mystery Lyon France physical location route collector city"],
+        )
+
+    async def _fallback(**_kwargs):
+        return LocationLLMFallbackResult(
+            candidates=[llm_candidate],
+            attempted_queries=["llm_factcheck:bgp_collector:rrc-mystery"],
+        )
+
+    monkeypatch.setattr(bgp_api, "get_ai_provider_client", AsyncMock(return_value=object()))
+    monkeypatch.setattr(bgp_api, "get_web_search_client", AsyncMock(return_value=object()))
+    monkeypatch.setattr(bgp_api, "collect_location_search_evidence", _search_evidence)
+    monkeypatch.setattr(bgp_api, "collect_llm_location_fallback_candidate", _fallback)
+
+    response = await bgp_api.collect_bgp_collector_location(
+        "rrc-mystery",
+        bgp_api.CollectBGPCollectorLocationRequest(city="Lyon", country="France"),
+        current_user=object(),
+        db=AsyncMock(),
+    )
+
+    assert response["success"] is True
+    assert response["best_candidate"]["source"] == "llm_location_factcheck"
+    assert response["best_candidate"]["needs_confirmation"] is True
+    assert response["attempted_queries"] == [
+        "Lyon, France",
+        "web_search:bgp_collector:rrc-mystery Lyon France physical location route collector city",
+        "llm_factcheck:bgp_collector:rrc-mystery",
+    ]
+
+
 # ── BGP event resolver ─────────────────────────────────────────────