fix(runtime): standardize 9000 startup and isolate project services

manage_plantai.sh

@@ -2,15 +2,19 @@
 # PlantAI-dev 9000 服务管理脚本
 # 用法: bash manage_plantai.sh {start|stop|restart|status} [--port PORT]
 # 默认端口: 9000
-#
-# 项目: /home/xzq/5090/teamWorkspace/zh/PlantAI-dev
-# 端口: 9000 (web), Redis DB 14 (queue prefix: plantai_dev_9002)
 
 set -euo pipefail
 
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+if [ -f "$SCRIPT_DIR/.env" ]; then
+    set -a
+    . "$SCRIPT_DIR/.env"
+    set +a
+fi
+
 # 解析命令行参数：第一个参数是命令，后面可选 --port / -p
 CMD=""
-WEB_PORT="9000"
+WEB_PORT="${PLANTAI_WEB_PORT:-9000}"
 for arg in "$@"; do
     case "$arg" in
         start|stop|restart|status)
@@ -33,12 +37,15 @@ done
 CMD="${CMD:-status}"
 
 # Conda 环境：启动脚本内部也依赖这个环境
-CONDA_ENV="${CONDA_ENV:-/home/xzq/miniconda3/envs/test4py311}"
+CONDA_BASE="${BBAV5_CONDA_BASE:-/home/xia-lab/miniconda3}"
+DEFAULT_ENV="${BBAV5_DEFAULT_ENV:-test4py311}"
+CONDA_ENV="${CONDA_ENV:-$CONDA_BASE/envs/$DEFAULT_ENV}"
 export PATH="$CONDA_ENV/bin:$PATH"
 
 # 项目配置（与 .env 和启动脚本保持一致）
-PROJECT_DIR="/home/xzq/5090/teamWorkspace/zh/PlantAI-dev"
+PROJECT_DIR="$SCRIPT_DIR"
-QUEUE_PREFIX="plantai_dev_9002"
+QUEUE_PREFIX="${BBAV5_QUEUE_PREFIX:-plantai_4090_9000}"
+REDIS_URL="${BBAV5_REDIS_URL:-redis://localhost:6379/10}"
 WEB_LOG="/tmp/plantai_${WEB_PORT}.log"
 CELERY_LOG="/tmp/celery_${WEB_PORT}.log"
 
@@ -46,28 +53,49 @@ red()  { echo -e "\033[31m$*\033[0m"; }
 green(){ echo -e "\033[32m$*\033[0m"; }
 cyan() { echo -e "\033[36m$*\033[0m"; }
 
+web_pid_for_port() {
+    ss -tlnp 2>/dev/null \
+        | grep ":$WEB_PORT " \
+        | grep -oP 'pid=\K\d+' \
+        | head -n 1 \
+        || true
+}
+
+web_process_cwd() {
+    readlink -f "/proc/$1/cwd" 2>/dev/null || true
+}
+
+web_pid_belongs_to_project() {
+    [ "$(web_process_cwd "$1")" = "$PROJECT_DIR" ]
+}
+
 status() {
     echo ""
     cyan "=== PlantAI-dev ${WEB_PORT} 服务状态 ==="
     echo ""
 
     # Web 服务
-    WEB_PID=$(ss -tlnp 2>/dev/null | grep ":$WEB_PORT " | grep -oP 'pid=\K\d+' || true)
+    WEB_PID="$(web_pid_for_port)"
     if [ -n "${WEB_PID:-}" ]; then
-        green "[✓] Web  服务运行中  (端口 $WEB_PORT, PID $WEB_PID)"
+        WEB_CWD="$(web_process_cwd "$WEB_PID")"
+        if web_pid_belongs_to_project "$WEB_PID"; then
+            green "[✓] Web  服务运行中  (端口 $WEB_PORT, PID $WEB_PID)"
+        else
+            red "[!] 端口 $WEB_PORT 被其他项目占用  (PID $WEB_PID, cwd ${WEB_CWD:-未知})"
+        fi
     else
         red "[✗] Web  服务未启动  (端口 $WEB_PORT)"
     fi
 
     # Redis
-    if redis-cli ping > /dev/null 2>&1; then
+    if redis-cli -u "$REDIS_URL" ping > /dev/null 2>&1; then
-        green "[✓] Redis 运行中  (localhost:6379)"
+        green "[✓] Redis 运行中  ($REDIS_URL)"
     else
         red "[✗] Redis 未启动"
     fi
 
     # Celery workers
-    CELERY_COUNT=$(pgrep -fc "$QUEUE_PREFIX" || echo 0)
+    CELERY_COUNT="$(pgrep -fc "$QUEUE_PREFIX" || true)"
     if [ "$CELERY_COUNT" -gt 0 ]; then
         green "[✓] Celery workers 运行中  (${CELERY_COUNT} 进程, 队列前缀: $QUEUE_PREFIX)"
         echo "    Worker 列表:"
@@ -86,13 +114,18 @@ stop() {
     echo ""
 
     # 停止 Web 服务
-    WEB_PID=$(ss -tlnp 2>/dev/null | grep ":$WEB_PORT " | grep -oP 'pid=\K\d+' || true)
+    WEB_PID="$(web_pid_for_port)"
     if [ -n "${WEB_PID:-}" ]; then
+        WEB_CWD="$(web_process_cwd "$WEB_PID")"
+        if ! web_pid_belongs_to_project "$WEB_PID"; then
+            red "[!] 拒绝停止：端口 $WEB_PORT 属于其他项目  (PID $WEB_PID, cwd ${WEB_CWD:-未知})"
+            return 1
+        fi
         echo "正在停止 Web 服务 (PID $WEB_PID)..."
         kill "$WEB_PID" 2>/dev/null || true
         sleep 1
-        # 如果还没死，强制 kill
+        # 仅强制停止仍属于本项目的原进程，避免 PID 复用造成误杀。
-        if ss -tlnp 2>/dev/null | grep -q ":$WEB_PORT"; then
+        if kill -0 "$WEB_PID" 2>/dev/null && web_pid_belongs_to_project "$WEB_PID"; then
             kill -9 "$WEB_PID" 2>/dev/null || true
         fi
         green "[✓] Web 服务已停止"
@@ -125,12 +158,18 @@ start() {
     echo ""
 
     # 检查是否已在运行
-    if ss -tlnp 2>/dev/null | grep -q ":$WEB_PORT"; then
+    WEB_PID="$(web_pid_for_port)"
-        red "[!] 端口 $WEB_PORT 已被占用，请先停止服务"
+    if [ -n "${WEB_PID:-}" ]; then
+        WEB_CWD="$(web_process_cwd "$WEB_PID")"
+        if web_pid_belongs_to_project "$WEB_PID"; then
+            red "[!] 本项目 Web 已在端口 $WEB_PORT 运行  (PID $WEB_PID)"
+        else
+            red "[!] 端口 $WEB_PORT 被其他项目占用  (PID $WEB_PID, cwd ${WEB_CWD:-未知})"
+        fi
         exit 1
     fi
 
-    if ! redis-cli ping > /dev/null 2>&1; then
+    if ! redis-cli -u "$REDIS_URL" ping > /dev/null 2>&1; then
         red "[!] Redis 未运行，请先启动 Redis"
         exit 1
     fi
@@ -141,7 +180,7 @@ start() {
     echo "正在启动 Celery workers..."
     nohup bash start_celery_9000.sh > "$CELERY_LOG" 2>&1 &
     sleep 3
-    CELERY_COUNT=$(pgrep -fc "$QUEUE_PREFIX" || echo 0)
+    CELERY_COUNT="$(pgrep -fc "$QUEUE_PREFIX" || true)"
     if [ "$CELERY_COUNT" -gt 0 ]; then
         green "  [✓] Celery workers 已启动 (${CELERY_COUNT} 进程)"
     else

start_celery_9000.sh

@@ -26,13 +26,13 @@ if [ -n "$EXTERNAL_BBAV5_WORKER_NAME_PREFIX" ]; then
     BBAV5_WORKER_NAME_PREFIX="$EXTERNAL_BBAV5_WORKER_NAME_PREFIX"
 fi
 if [ -z "${BBAV5_QUEUE_PREFIX-}" ]; then
-    BBAV5_QUEUE_PREFIX="plantai_dev_9000"
+    BBAV5_QUEUE_PREFIX="plantai_4090_9000"
 fi
 if [ -z "${BBAV5_REDIS_URL-}" ]; then
     BBAV5_REDIS_URL="redis://localhost:6379/10"
 fi
 if [ -z "${BBAV5_CELERY_LOG_DIR-}" ]; then
-    BBAV5_CELERY_LOG_DIR="logs/celery_plantai_dev_9000"
+    BBAV5_CELERY_LOG_DIR="logs/celery_plantai_4090_9000"
 fi
 if [ -z "$EXTERNAL_BBAV5_WORKER_NAME_PREFIX" ]; then
     unset BBAV5_WORKER_NAME_PREFIX
@@ -51,11 +51,11 @@ export BBAV5_PROJECT_ENV_FILE="${BBAV5_PROJECT_ENV_FILE:-$PROJECT_ROOT/.env}"
 export BBAV5_LIGHTWEIGHT_EXTENSION_STORE="${BBAV5_LIGHTWEIGHT_EXTENSION_STORE:-$PROJECT_ROOT/.runtime/lightweight-extension/store}"
 export BBAV5_LIGHTWEIGHT_INPUT="${BBAV5_LIGHTWEIGHT_INPUT:-$PROJECT_ROOT/input}"
 export BBAV5_LIGHTWEIGHT_WORKSPACE="${BBAV5_LIGHTWEIGHT_WORKSPACE:-$PROJECT_ROOT/workspace}"
-export BBAV5_QUEUE_PREFIX="${BBAV5_QUEUE_PREFIX:-plantai_dev_9000}"
+export BBAV5_QUEUE_PREFIX="${BBAV5_QUEUE_PREFIX:-plantai_4090_9000}"
 export BBAV5_REDIS_URL="${BBAV5_REDIS_URL:-redis://localhost:6379/10}"
 WORKER_NAME_PREFIX="${BBAV5_WORKER_NAME_PREFIX:-${BBAV5_QUEUE_PREFIX//[^A-Za-z0-9_]/_}}"
 
-LOG_DIR="${BBAV5_CELERY_LOG_DIR:-logs/celery_plantai_dev_9000}"
+LOG_DIR="${BBAV5_CELERY_LOG_DIR:-logs/celery_plantai_4090_9000}"
 mkdir -p "$LOG_DIR"
 
 CELERY="$CONDA_ENV/bin/celery"

start_plantai_9000.sh

@@ -24,6 +24,12 @@ done
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 cd "$SCRIPT_DIR"
 
+if [ -f "$SCRIPT_DIR/.env" ]; then
+    set -a
+    . "$SCRIPT_DIR/.env"
+    set +a
+fi
+
 CONDA_BASE="${BBAV5_CONDA_BASE:-/home/xia-lab/miniconda3}"
 DEFAULT_ENV="${BBAV5_DEFAULT_ENV:-test4py311}"
 CONDA_ENV="$CONDA_BASE/envs/$DEFAULT_ENV"
@@ -33,23 +39,18 @@ export PATH="$CONDA_ENV/bin:$PATH"
 # the caller's shell; GWAS/other sandboxes have dedicated restart scripts.
 export BBAV5_PROJECT_ROOT="$SCRIPT_DIR"
 export PLANTAI_PROJECT_ROOT="$SCRIPT_DIR"
-if [ -f "$SCRIPT_DIR/.env" ]; then
-    set -a
-    . "$SCRIPT_DIR/.env"
-    set +a
-fi
 export BBAV5_PROJECT_ENV_FILE="${BBAV5_PROJECT_ENV_FILE:-$SCRIPT_DIR/.env}"
 export BBAV5_LIGHTWEIGHT_EXTENSION_STORE="${BBAV5_LIGHTWEIGHT_EXTENSION_STORE:-$SCRIPT_DIR/.runtime/lightweight-extension/store}"
 export BBAV5_LIGHTWEIGHT_INPUT="${BBAV5_LIGHTWEIGHT_INPUT:-$SCRIPT_DIR/input}"
 export BBAV5_LIGHTWEIGHT_WORKSPACE="${BBAV5_LIGHTWEIGHT_WORKSPACE:-$SCRIPT_DIR/workspace}"
-export BBAV5_QUEUE_PREFIX="${BBAV5_QUEUE_PREFIX:-plantai_dev_9000}"
+export BBAV5_QUEUE_PREFIX="${BBAV5_QUEUE_PREFIX:-plantai_4090_9000}"
 export BBAV5_REDIS_URL="${BBAV5_REDIS_URL:-redis://localhost:6379/10}"
 export PLANTAI_WEB_PORT="$PORT"
 export PLANTAI_RESTART_SCRIPT="$SCRIPT_DIR/restart_plantai_9000.sh"
-export GENE_FAMILY_MAS_API="http://127.0.0.1:7926"
+export GENE_FAMILY_MAS_API="${GENE_FAMILY_MAS_API:-${DUAL_KB_QA_BASE_URL:-http://127.0.0.1:7920}}"
-export DUAL_KB_QA_BASE_URL="http://127.0.0.1:7926"
+export DUAL_KB_QA_BASE_URL="${DUAL_KB_QA_BASE_URL:-$GENE_FAMILY_MAS_API}"
-export RAG_API_URL="http://127.0.0.1:7926/api/v1/qa-v1-1-73/chat"
+export RAG_API_URL="${RAG_API_URL:-$GENE_FAMILY_MAS_API}"
-export DUAL_KB_QA_ROUTE="qa-v1-1-73"
+export DUAL_KB_QA_ROUTE="${DUAL_KB_QA_ROUTE:-qa-v1-1-73}"
 export PLANTAI_AGENT_STATE_DB="$SCRIPT_DIR/.runtime/agent-state/agent-state.sqlite3"
 
 PORT="$PLANTAI_WEB_PORT"