优化 run.sh 三种部署方式的升级清理逻辑

- 共用 clean/build 函数，升级前清理 frontend/dist、backend/static 与旧二进制
- binary upgrade/start/stop/status：停服、备份、重编译、后台启动并持久化启动参数
- docker up/upgrade：--force-recreate --remove-orphans，支持 up fresh 无缓存重建
- kubernetes upgrade：--no-cache 构建 + 时间戳镜像 tag，set image 触发滚动更新

run.sh

@@ -14,7 +14,8 @@
 #
 #   方式 3 — 独立二进制:
 #     ./run.sh build               编译独立二进制 (embed 前端)
-#     ./run.sh binary              编译并启动
+#     ./run.sh binary upgrade      停服 → 清旧产物 → 重编译 → 后台启动
+#     ./run.sh binary start|stop|status
 #
 #   本地开发:
 #     ./run.sh dev                 前后端热重载
@@ -60,6 +61,8 @@ cd "$SCRIPT_DIR"
 # PID 文件
 BACKEND_PID_FILE="$SCRIPT_DIR/$BACKEND_DIR/.backend.pid"
 FRONTEND_PID_FILE="$SCRIPT_DIR/$FRONTEND_DIR/.frontend.pid"
+BINARY_PID_FILE="$SCRIPT_DIR/$BACKEND_DIR/.aiops.pid"
+BINARY_ARGS_FILE="$SCRIPT_DIR/$BACKEND_DIR/.aiops.args"
 
 # 检测操作系统
 detect_os() {
@@ -290,6 +293,196 @@ cmd_logs() {
     wait
 }
 
+# ============================================================
+# 构建清理（三种部署方式共用，避免旧代码/旧静态资源残留）// Logan.Li
+# ============================================================
+clean_frontend_artifacts() {
+    info "清理前端旧构建产物..."
+    rm -rf "$SCRIPT_DIR/$FRONTEND_DIR/dist"
+    rm -rf "$SCRIPT_DIR/$FRONTEND_DIR/node_modules/.vite"
+}
+
+clean_embed_static() {
+    info "清理 embed static 旧文件..."
+    mkdir -p "$SCRIPT_DIR/$BACKEND_DIR/static"
+    find "$SCRIPT_DIR/$BACKEND_DIR/static" -mindepth 1 -delete 2>/dev/null || rm -rf "$SCRIPT_DIR/$BACKEND_DIR/static"/*
+}
+
+clean_go_artifacts() {
+    info "清理 Go 旧编译产物..."
+    rm -f "$SCRIPT_DIR/$BACKEND_DIR/$STANDALONE_BIN"
+    rm -f "$SCRIPT_DIR/$BACKEND_DIR/$BACKEND_BIN"
+}
+
+# 构建前端并同步到 backend/static（二进制 / embed 镜像共用）// Logan.Li
+build_frontend_embed() {
+    clean_frontend_artifacts
+    cd "$SCRIPT_DIR/$FRONTEND_DIR"
+    if [ ! -d "node_modules" ]; then
+        npm install --registry=https://registry.npmmirror.com
+    fi
+    npm run build 2>&1 | tail -8
+    cd "$SCRIPT_DIR"
+    clean_embed_static
+    cp -r "$FRONTEND_DIR/dist/"* "$BACKEND_DIR/static/"
+    local fe_files
+    fe_files=$(find "$BACKEND_DIR/static" -type f | wc -l | tr -d ' ')
+    success "前端已嵌入 static/ ($fe_files 个文件)"
+}
+
+# 停止独立二进制进程（PID 文件 + 端口双保险）// Logan.Li
+stop_binary_process() {
+    local port=${1:-8080}
+    if [ -f "$BINARY_PID_FILE" ]; then
+        local pid
+        pid=$(cat "$BINARY_PID_FILE" 2>/dev/null || echo "")
+        if [ -n "$pid" ] && kill -0 "$pid" 2>/dev/null; then
+            kill "$pid" 2>/dev/null || true
+            sleep 1
+            kill -9 "$pid" 2>/dev/null || true
+            success "已停止二进制进程 (PID: $pid)"
+        fi
+        rm -f "$BINARY_PID_FILE"
+    fi
+    # 兜底：按端口和进程名清理残留
+    if [ "$OS" = "macos" ]; then
+        local pids
+        pids=$(lsof -ti:"$port" 2>/dev/null || echo "")
+        [ -n "$pids" ] && echo "$pids" | xargs kill -9 2>/dev/null || true
+    else
+        fuser -k "${port}/tcp" 2>/dev/null || true
+        pkill -f "${SCRIPT_DIR}/${BACKEND_DIR}/${STANDALONE_BIN}" 2>/dev/null || true
+        pkill -f "./${STANDALONE_BIN} --port" 2>/dev/null || true
+    fi
+    sleep 0.5
+}
+
+wait_binary_ready() {
+    local port=${1:-8080}
+    local retries=0
+    while ! curl -sf "http://localhost:${port}/version" > /dev/null 2>&1; do
+        retries=$((retries + 1))
+        if [ $retries -ge 30 ]; then
+            error "二进制启动超时，查看日志: $BACKEND_DIR/logs/aiops.log"
+            tail -20 "$SCRIPT_DIR/$BACKEND_DIR/logs/aiops.log" 2>/dev/null || true
+            return 1
+        fi
+        sleep 1
+    done
+    return 0
+}
+
+# 确保二进制默认 config.yaml 存在 // Logan.Li
+ensure_binary_config() {
+    local cfg="$SCRIPT_DIR/$BACKEND_DIR/config.yaml"
+    if [ -f "$cfg" ]; then
+        return 0
+    fi
+    info "生成默认 config.yaml (SQLite + 无Redis)..."
+    cat > "$cfg" << 'YAML'
+mode: "release"
+port: "8080"
+log_level: "info"
+
+database:
+  driver: "sqlite"
+  host: "localhost"
+  port: 3306
+  user: ""
+  password: ""
+  dbname: "data/aiops.db"
+  charset: "utf8mb4"
+  max_conn: 100
+  max_idle: 10
+
+redis:
+  host: "localhost"
+  port: 6379
+  password: ""
+  db: 0
+
+jwt:
+  secret: "CHANGE_ME_JWT_SECRET"  # ⚠️ 生产环境必须替换
+  expire_hour: 24
+
+websocket:
+  read_buffer_size: 1024
+  write_buffer_size: 1024
+YAML
+}
+
+# 编译独立二进制（含 embed 前端）// Logan.Li
+build_standalone_binary() {
+    build_frontend_embed
+    ensure_binary_config
+    clean_go_artifacts
+    cd "$SCRIPT_DIR/$BACKEND_DIR"
+    info "编译中..."
+    CGO_ENABLED=1 GOPROXY=https://goproxy.cn,direct GONOSUMCHECK='*' GOTOOLCHAIN=go1.24.0 \
+        go build -ldflags="-w -s" -o "$STANDALONE_BIN" .
+    if [ ! -f "$STANDALONE_BIN" ]; then
+        error "编译失败"
+        return 1
+    fi
+    local bin_size
+    bin_size=$(du -h "$STANDALONE_BIN" | cut -f1)
+    success "编译完成: $BACKEND_DIR/$STANDALONE_BIN ($bin_size)"
+    cd "$SCRIPT_DIR"
+    return 0
+}
+
+# 解析/持久化二进制启动参数 // Logan.Li
+save_binary_args() {
+    printf '%s\n' "$@" > "$BINARY_ARGS_FILE"
+}
+
+load_binary_args() {
+    local -n _out=$1
+    _out=()
+    if [ -f "$BINARY_ARGS_FILE" ]; then
+        while IFS= read -r line || [ -n "$line" ]; do
+            [ -n "$line" ] && _out+=("$line")
+        done < "$BINARY_ARGS_FILE"
+    fi
+    if [ ${#_out[@]} -eq 0 ]; then
+        _out=(--port 8080 --db-driver sqlite)
+    fi
+}
+
+binary_listen_port() {
+    local args=("$@")
+    local i=0
+    while [ $i -lt ${#args[@]} ]; do
+        if [ "${args[$i]}" = "--port" ] && [ $((i + 1)) -lt ${#args[@]} ]; then
+            echo "${args[$((i + 1))]}"
+            return 0
+        fi
+        i=$((i + 1))
+    done
+    echo "8080"
+}
+
+# 后台启动独立二进制 // Logan.Li
+start_binary_daemon() {
+    local args=("$@")
+    local port
+    port=$(binary_listen_port "${args[@]}")
+    cd "$SCRIPT_DIR/$BACKEND_DIR"
+    mkdir -p data logs uploads
+    rotate_log "logs/aiops.log"
+    stop_binary_process "$port"
+    nohup ./"$STANDALONE_BIN" "${args[@]}" >> logs/aiops.log 2>&1 &
+    echo $! > "$BINARY_PID_FILE"
+    save_binary_args "${args[@]}"
+    if wait_binary_ready "$port"; then
+        success "二进制已启动 (PID: $(cat "$BINARY_PID_FILE"), 端口: $port)"
+        info "日志: $BACKEND_DIR/logs/aiops.log"
+        info "健康检查: http://localhost:${port}/version"
+        return 0
+    fi
+    return 1
+}
+
 # ============================================================
 # Docker Compose 部署
 # ============================================================
@@ -331,9 +524,21 @@ cmd_docker() {
     info "BuildKit: 已启用 (增量编译 + 缓存复用)"
 
     case "$action" in
-        up)
+        up|upgrade|update)
-            banner "========== Docker Compose 启动 =========="
+            local fresh_build=0
-            $DOCKER_COMPOSE up -d --build
+            if [ "${2:-}" = "fresh" ] || [ "$action" = "fresh" ]; then
+                fresh_build=1
+            fi
+            banner "========== Docker Compose 启动/升级 =========="
+            clean_frontend_artifacts
+            if [ "$fresh_build" -eq 1 ]; then
+                info "全量重建镜像 (--no-cache)..."
+                $DOCKER_COMPOSE build --no-cache
+                $DOCKER_COMPOSE up -d --force-recreate --remove-orphans
+            else
+                info "增量构建 + 强制重建容器..."
+                $DOCKER_COMPOSE up -d --build --force-recreate --remove-orphans
+            fi
             echo ""
             # 清理历史 build cache 和悬空镜像，防止占满磁盘
             info "清理历史构建缓存..."
@@ -389,15 +594,20 @@ cmd_docker() {
             echo "  $(df -h / | awk 'NR==2{print $3, "used /", $2, "total ("$5")"}')"
             success "清理完成"
             ;;
+        fresh)
+            cmd_docker up fresh
+            ;;
         help|--help|-h)
             echo "Docker Compose 部署命令:"
-            echo "  ./run.sh docker up        构建并启动所有容器"
+            echo "  ./run.sh docker up          增量构建 + 强制重建容器"
-            echo "  ./run.sh docker down      停止并移除容器"
+            echo "  ./run.sh docker up fresh    无缓存全量重建镜像并启动"
-            echo "  ./run.sh docker build     仅构建镜像"
+            echo "  ./run.sh docker upgrade     同 up（升级别名）"
-            echo "  ./run.sh docker restart   重启容器"
+            echo "  ./run.sh docker down        停止并移除容器"
-            echo "  ./run.sh docker logs      查看实时日志"
+            echo "  ./run.sh docker build       仅构建镜像"
-            echo "  ./run.sh docker ps        查看容器状态"
+            echo "  ./run.sh docker restart     重启容器"
-            echo "  ./run.sh docker clean     清理构建缓存/无用镜像"
+            echo "  ./run.sh docker logs        查看实时日志"
+            echo "  ./run.sh docker ps          查看容器状态"
+            echo "  ./run.sh docker clean       清理构建缓存/无用镜像"
             ;;
         *)
             error "未知 docker 子命令: $action"
@@ -416,78 +626,12 @@ cmd_build() {
     case "$target" in
         binary|aiops)
             banner "========== 编译独立二进制 =========="
-
+            build_standalone_binary || exit 1
-            # 构建前端 → 拷贝到 embed 目录（go:embed 需要 static/ 下有文件）
+            echo ""
-            info "构建前端 → embed..."
+            info "使用方法:"
-            cd "$SCRIPT_DIR/$FRONTEND_DIR"
+            echo "  ./run.sh binary upgrade                               # 停服重编译并后台启动"
-            if [ ! -d "node_modules" ]; then
+            echo "  ./$BACKEND_DIR/$STANDALONE_BIN --port 8080            # 前台启动"
-                npm install --registry=https://registry.npmmirror.com
+            echo "  ./$BACKEND_DIR/$STANDALONE_BIN --config config.yaml   # 使用配置文件"
-            fi
-            npm run build 2>&1 | tail -5
-
-            # 拷贝前端构建产物到后端 embed 目录
-            cd "$SCRIPT_DIR"
-            rm -rf "$BACKEND_DIR/static"/*
-            cp -r "$FRONTEND_DIR/dist/"* "$BACKEND_DIR/static/"
-            local fe_files=$(find "$BACKEND_DIR/static" -type f | wc -l)
-            success "前端已嵌入 ($fe_files 文件)"
-
-            cd "$SCRIPT_DIR/$BACKEND_DIR"
-
-            # 确保 config.yaml 存在（二进制模式默认 SQLite）
-            if [ ! -f "config.yaml" ]; then
-                info "生成默认 config.yaml (SQLite + 无Redis)..."
-                cat > config.yaml << 'YAML'
-mode: "release"
-port: "8080"
-log_level: "info"
-
-database:
-  driver: "sqlite"
-  host: "localhost"
-  port: 3306
-  user: ""
-  password: ""
-  dbname: "data/aiops.db"
-  charset: "utf8mb4"
-  max_conn: 100
-  max_idle: 10
-
-redis:
-  host: "localhost"
-  port: 6379
-  password: ""
-  db: 0
-
-jwt:
-  secret: "CHANGE_ME_JWT_SECRET"  # ⚠️ 生产环境必须替换
-  expire_hour: 24
-
-websocket:
-  read_buffer_size: 1024
-  write_buffer_size: 1024
-YAML
-            fi
-
-            # 静态编译（CGO_ENABLED=1 因为 SQLite 需要 CGO）
-            info "编译中..."
-            CGO_ENABLED=1 GOPROXY=https://goproxy.cn,direct GONOSUMCHECK='*' GOTOOLCHAIN=go1.24.0 go build -ldflags="-w -s" -o "$STANDALONE_BIN" .
-
-            if [ -f "$STANDALONE_BIN" ]; then
-                local bin_size=$(du -h "$STANDALONE_BIN" | cut -f1)
-                success "编译完成: $BACKEND_DIR/$STANDALONE_BIN ($bin_size)"
-                echo ""
-                info "使用方法:"
-                echo "  ./$BACKEND_DIR/$STANDALONE_BIN                        # 默认启动 (SQLite, 端口 8080)"
-                echo "  ./$BACKEND_DIR/$STANDALONE_BIN --port 9090            # 自定义端口"
-                echo "  ./$BACKEND_DIR/$STANDALONE_BIN --db-driver mysql \\"
-                echo "      --db-host localhost --db-user root \\"
-                echo "      --db-password pass --db-name aiops                 # MySQL 模式"
-                echo "  ./$BACKEND_DIR/$STANDALONE_BIN --config config.yaml    # 使用配置文件"
-            else
-                error "编译失败"
-                exit 1
-            fi
             ;;
         agent)
             banner "========== 编译 Agent =========="
@@ -531,19 +675,96 @@ YAML
 # 独立二进制模式
 # ============================================================
 cmd_binary() {
-    cd "$SCRIPT_DIR/$BACKEND_DIR"
+    local action="run"
-
+    if [ $# -gt 0 ] && [[ "$1" =~ ^(upgrade|start|stop|status|help|--help|-h)$ ]]; then
-    # 先编译（如果不存在）
+        action=$1
-    if [ ! -f "$STANDALONE_BIN" ]; then
+        shift
-        info "二进制不存在，先编译..."
-        cmd_build binary
     fi
 
-    banner "========== 启动独立二进制 =========="
+    case "$action" in
-    mkdir -p data logs uploads
+        upgrade|update)
-
+            banner "========== 二进制升级部署 =========="
-    # 传递额外参数
+            local args=()
-    ./"$STANDALONE_BIN" "$@"
+            if [ $# -gt 0 ]; then
+                args=("$@")
+            else
+                load_binary_args args
+            fi
+            local port
+            port=$(binary_listen_port "${args[@]}")
+            info "启动参数: ${args[*]}"
+            stop_binary_process "$port"
+            if [ -f "$SCRIPT_DIR/$BACKEND_DIR/$STANDALONE_BIN" ]; then
+                local backup="$SCRIPT_DIR/$BACKEND_DIR/${STANDALONE_BIN}.bak.$(date +%Y%m%d%H%M%S)"
+                cp "$SCRIPT_DIR/$BACKEND_DIR/$STANDALONE_BIN" "$backup"
+                info "已备份旧二进制: $backup"
+            fi
+            build_standalone_binary || exit 1
+            start_binary_daemon "${args[@]}" || exit 1
+            ;;
+        start)
+            local args=()
+            if [ $# -gt 0 ]; then
+                args=("$@")
+            else
+                load_binary_args args
+            fi
+            if [ ! -f "$SCRIPT_DIR/$BACKEND_DIR/$STANDALONE_BIN" ]; then
+                info "二进制不存在，先编译..."
+                build_standalone_binary || exit 1
+            fi
+            start_binary_daemon "${args[@]}" || exit 1
+            ;;
+        stop)
+            local port=${1:-8080}
+            stop_binary_process "$port"
+            success "二进制已停止"
+            ;;
+        status)
+            local args=()
+            load_binary_args args
+            local port
+            port=$(binary_listen_port "${args[@]}")
+            info "监听端口: $port"
+            if [ -f "$BINARY_PID_FILE" ]; then
+                local pid
+                pid=$(cat "$BINARY_PID_FILE" 2>/dev/null || echo "")
+                if [ -n "$pid" ] && kill -0 "$pid" 2>/dev/null; then
+                    success "进程运行中 (PID: $pid)"
+                else
+                    warning "PID 文件存在但进程未运行"
+                fi
+            else
+                warning "未找到 PID 文件"
+            fi
+            if curl -sf "http://localhost:${port}/version" > /dev/null 2>&1; then
+                success "HTTP 就绪: http://localhost:${port}/version"
+            else
+                warning "HTTP 未响应"
+            fi
+            ;;
+        help|--help|-h)
+            echo "独立二进制命令:"
+            echo "  ./run.sh binary upgrade [--port 8080 --db-driver sqlite]  停服→清旧→重编译→启动"
+            echo "  ./run.sh binary start   [args...]                           后台启动（参数会持久化）"
+            echo "  ./run.sh binary stop    [port]                            停止进程"
+            echo "  ./run.sh binary status                                    查看状态"
+            echo "  ./run.sh binary [--port 8080 ...]                         前台运行（开发调试）"
+            ;;
+        run|*)
+            cd "$SCRIPT_DIR/$BACKEND_DIR"
+            if [ ! -f "$STANDALONE_BIN" ]; then
+                info "二进制不存在，先编译..."
+                build_standalone_binary || exit 1
+            fi
+            banner "========== 前台启动独立二进制 =========="
+            mkdir -p data logs uploads
+            if [ $# -gt 0 ]; then
+                save_binary_args "$@"
+            fi
+            ./"$STANDALONE_BIN" "$@"
+            ;;
+    esac
 }
 
 # ============================================================
@@ -553,6 +774,7 @@ KUBERNETES_NAMESPACE="devops"
 KUBERNETES_MANIFEST_DIR="$SCRIPT_DIR/deploy/kubernetes"
 KUBERNETES_IMAGE="aiops:embed"
 KUBERNETES_NODE_PORT=30080
+KUBERNETES_BUILT_IMAGE=""
 
 # 检测 kubectl 和 Docker
 check_kubernetes_deps() {
@@ -592,34 +814,52 @@ load_image_to_cluster() {
     warning "如集群无法拉取镜像，请手动推送: docker push <registry>/$image"
 }
 
-# Kubernetes 构建镜像
+# Kubernetes 构建镜像（upgrade 时无缓存 + 时间戳 tag 避免旧层残留）// Logan.Li
 cmd_kubernetes_build() {
+    local no_cache=${1:-0}
     if ! command -v docker &>/dev/null; then
         error "Docker 未安装"
         exit 1
     fi
 
     banner "========== 构建 embed 镜像 =========="
-    info "镜像: $KUBERNETES_IMAGE"
+    clean_frontend_artifacts
+    clean_embed_static
 
-    # 版本信息
+    local version
-    local version=$(git describe --tags --abbrev=0 2>/dev/null || echo "dev")
+    version=$(git describe --tags --abbrev=0 2>/dev/null || echo "dev")
-    local build_time=$(date -u +%Y-%m-%dT%H:%M:%SZ)
+    local build_time
+    build_time=$(date -u +%Y-%m-%dT%H:%M:%SZ)
+    local image_tag
+    image_tag="${KUBERNETES_IMAGE}-$(date +%Y%m%d%H%M%S)"
+    info "镜像: $KUBERNETES_IMAGE (+ $image_tag)"
+
+    local build_args=(
+        -f Dockerfile.embed
+        --build-arg VERSION="$version"
+        --build-arg BUILD_TIME="$build_time"
+        -t "$KUBERNETES_IMAGE"
+        -t "$image_tag"
+    )
+    if [ "$no_cache" -eq 1 ]; then
+        build_args+=(--no-cache --pull)
+        info "无缓存全量构建 (--no-cache --pull)"
+    fi
+    build_args+=(.)
 
     info "构建中（前端 + 后端 embed）..."
-    docker build -f Dockerfile.embed \
+    docker build "${build_args[@]}" || {
-        --build-arg VERSION="$version" \
-        --build-arg BUILD_TIME="$build_time" \
-        -t "$KUBERNETES_IMAGE" . || {
         error "镜像构建失败"
         exit 1
     }
 
-    local img_size=$(docker images "$KUBERNETES_IMAGE" --format "{{.Size}}" | head -1)
+    local img_size
+    img_size=$(docker images "$KUBERNETES_IMAGE" --format "{{.Size}}" | head -1)
     success "镜像构建完成: $KUBERNETES_IMAGE ($img_size)"
 
-    # 加载到本地集群
     load_image_to_cluster "$KUBERNETES_IMAGE"
+    load_image_to_cluster "$image_tag"
+    KUBERNETES_BUILT_IMAGE="$image_tag"
 }
 
 # Kubernetes 部署
@@ -678,10 +918,12 @@ cmd_kubernetes() {
         upgrade|update)
             check_kubernetes_deps
             banner "========== Kubernetes 滚动更新 =========="
-            cmd_kubernetes_build
+            cmd_kubernetes_build 1
-            info "触发滚动更新..."
+            info "更新 Deployment 镜像: $KUBERNETES_BUILT_IMAGE"
-            kubectl -n "$KUBERNETES_NAMESPACE" rollout restart deployment/aiops
+            kubectl -n "$KUBERNETES_NAMESPACE" set image deployment/aiops aiops="$KUBERNETES_BUILT_IMAGE" --record
             kubectl -n "$KUBERNETES_NAMESPACE" rollout status deployment/aiops --timeout=180s
+            info "清理悬空镜像..."
+            docker image prune -f 2>/dev/null || true
             success "滚动更新完成"
             ;;
 
@@ -812,7 +1054,9 @@ cmd_help() {
     echo "    ./run.sh logs               查看实时日志"
     echo ""
     echo -e "  ${CYAN}Docker 容器部署${NC}"
-    echo "    ./run.sh docker up          构建并启动所有容器 (MySQL+Redis+Nginx)"
+    echo "    ./run.sh docker up          增量构建 + 强制重建容器"
+    echo "    ./run.sh docker up fresh    无缓存全量重建并启动"
+    echo "    ./run.sh docker upgrade     同 up（升级别名）"
     echo "    ./run.sh docker down        停止并移除容器"
     echo "    ./run.sh docker build       仅构建镜像"
     echo "    ./run.sh docker restart     重启容器"
@@ -834,7 +1078,9 @@ cmd_help() {
     echo ""
     echo -e "  ${YELLOW}编译 & 独立二进制${NC}"
     echo "    ./run.sh build              编译独立二进制 ./$BACKEND_DIR/$STANDALONE_BIN"
-    echo "    ./run.sh binary             编译+启动独立二进制"
+    echo "    ./run.sh binary upgrade     停服→清旧→重编译→后台启动（生产升级）"
+    echo "    ./run.sh binary start|stop|status  进程管理"
+    echo "    ./run.sh binary [args]      前台启动（调试）"
     echo "    ./run.sh build agent        交叉编译 Agent (amd64+arm64)"
     echo "    ./run.sh build frontend     构建前端生产包"
     echo ""