fix: repair session API and local session fallback

README.md

@@ -177,6 +177,28 @@ Agent 只主动连接 Hub，不需要公网入站端口。
 
 ---
 
+## 🚀 一键安装与升级
+
+### 一键安装
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/kyaring/vps-commander/main/deploy/install.sh | sudo bash
+```
+
+安装脚本自动识别 `amd64/arm64` 并进入 Hub / Agent 安装流程。
+
+### 一键升级 Agent
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/kyaring/vps-commander/main/deploy/upgrade-agent.sh | sudo bash
+```
+
+升级脚本下载目标 Release、校验文件大小、备份旧版本并在启动失败时自动回滚。
+
+生产环境的 Agent 凭据以独立设备凭据为准；不要将 Cluster Secret 作为长期生产凭据重新启用。
+
+---
+
 ## 📄 文档索引
 
 - [文档基线与全局索引](docs/DOCUMENTATION_BASELINE_20261002.md)

cmd/hub/main.go

@@ -70,6 +70,7 @@ func main() {
 		AdminToken:    adminToken,
 		ExecLimiter:   make(chan struct{}, 32),
 		SearchLimiter: make(chan struct{}, 8),
+		LocalSessions: executor.NewSessionManager(0),
 	}
 	if err := s.LoadSecurityPolicySnapshot(); err != nil {
 		log.Fatalf("load security policy snapshot: %v", err)
@@ -121,6 +122,13 @@ func main() {
 		IdleTimeout:       90 * time.Second,
 	}
 	log.Printf("vps-commander-hub listening on %s as %s", *addr, local)
+	go func() {
+		ticker := time.NewTicker(time.Minute)
+		defer ticker.Stop()
+		for range ticker.C {
+			s.LocalSessions.Cleanup()
+		}
+	}()
 	go func() {
 		if err := server.ListenAndServe(); err != nil && err != http.ErrServerClosed {
 			log.Fatal(err)

deploy/README.md

@@ -47,9 +47,53 @@ chmod 0600 /etc/vps-commander/agent.env
 
 ---
 
-## 三、Hub 服务端部署步骤
+## 三、一键安装与升级
 
-### 3.1 编译
+### 3.1 一键安装
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/kyaring/vps-commander/main/deploy/install.sh | sudo bash
+```
+
+脚本自动识别 `amd64/arm64`，并进入 Hub / Agent 安装流程。
+
+- Hub：自动生成 API Key 与 Web 面板密码。
+- Agent：输入 Hub WSS 地址、节点名称和独立 Agent Token。
+- 生产环境不再要求 Cluster Secret 作为长期凭据。
+
+### 3.2 一键升级 Agent
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/kyaring/vps-commander/main/deploy/upgrade-agent.sh | sudo bash
+```
+
+升级流程：
+
+```text
+下载 Release
+   ↓
+临时文件完整性检查
+   ↓
+备份当前 Agent
+   ↓
+原子替换
+   ↓
+systemd restart
+   ↓
+健康检查
+   ├─ 成功 → 删除备份
+   └─ 失败 → 自动恢复旧版本
+```
+
+### 3.3 手工安装
+
+如果需要固定版本、离线部署或灰度验证，再使用下面的手工安装流程。
+
+---
+
+## 四、Hub 服务端部署步骤
+
+### 4.1 编译
 ```bash
 cd /root/.openclaw/workspace/vps-commander
 go test ./...
@@ -65,13 +109,13 @@ vcs.modified=false
 vcs.revision=<release commit>
 ```
 
-### 3.2 安装
+### 4.2 安装
 ```bash
 install -d -m 0750 /opt/vps-commander/data /etc/vps-commander
 install -m 0755 bin/vps-commander-hub-linux-amd64 /opt/vps-commander/vps-commander-hub
 ```
 
-### 3.3 配置
+### 4.3 配置
 ```bash
 cat << 'ENV' > /etc/vps-commander/hub.env
 VPS_COMMANDER_API_KEY=your_secure_api_key
@@ -80,7 +124,7 @@ ENV
 chmod 0600 /etc/vps-commander/hub.env
 ```
 
-### 3.4 Systemd
+### 4.4 Systemd
 ```ini
 [Service]
 EnvironmentFile=-/etc/vps-commander/hub.env
@@ -89,7 +133,7 @@ Restart=always
 RestartSec=3s
 ```
 
-### 3.5 启动
+### 4.5 启动
 ```bash
 systemctl daemon-reload
 systemctl enable --now vps-commander-hub
@@ -98,15 +142,15 @@ systemctl status vps-commander-hub
 
 ---
 
-## 四、远程 Agent 节点部署步骤
+## 五、远程 Agent 节点部署步骤
 
-### 4.1 安装二进制
+### 5.1 安装二进制
 ```bash
 install -d -m 0750 /etc/vps-commander /opt/vps-commander
 install -m 0755 vps-commander-agent-linux-amd64 /opt/vps-commander/vps-commander-agent
 ```
 
-### 4.2 配置
+### 5.2 配置
 ```bash
 cat << 'ENV' > /etc/vps-commander/agent.env
 VPS_COMMANDER_HUB_WS_URL=wss://vpstool.kory.kdns.fr/agent/ws
@@ -116,7 +160,7 @@ ENV
 chmod 0600 /etc/vps-commander/agent.env
 ```
 
-### 4.3 Systemd
+### 5.3 Systemd
 ```ini
 [Service]
 EnvironmentFile=-/etc/vps-commander/agent.env
@@ -127,7 +171,7 @@ RestartSec=3s
 
 当前 v2.0 生产迁移阶段可兼容显式 token；v2.1 发布后必须改为不出现在 ExecStart 的方式。
 
-### 4.4 启动
+### 5.4 启动
 ```bash
 systemctl daemon-reload
 systemctl enable --now vps-commander-agent
@@ -138,14 +182,14 @@ Agent 启动后主动连接 Hub，并在设备列表中显示为 `online`。
 
 ---
 
-## 五、控制面板与 MCP 使用
+## 六、控制面板与 MCP 使用
 
-### 5.1 管理面板
+### 6.1 管理面板
 `https://vpstool.kory.kdns.fr/panel/login`
 
 面板包含设备状态、安全策略、操作控制、审计和相关管理功能。
 
-### 5.2 MCP
+### 6.2 MCP
 远程入口：
 `https://vpstool.kory.kdns.fr/mcp/sse`
 
@@ -155,7 +199,7 @@ Agent 启动后主动连接 Hub，并在设备列表中显示为 `online`。
 
 ---
 
-## 六、生产升级流程
+## 七、生产升级流程
 
 ```text
 Backup
@@ -177,7 +221,7 @@ Full Acceptance
 
 ---
 
-## 七、日常运维检查
+## 八、日常运维检查
 
 ```bash
 systemctl status vps-commander-hub
@@ -189,7 +233,7 @@ curl -fsS http://127.0.0.1:9521/healthz
 
 ---
 
-## 八、当前生产审计提示
+## 九、当前生产审计提示
 
 2026-10-02 审计发现生产 Hub / Agent 曾由 `vcs.modified=true` 的工作树构建。
 因此生产现场二进制不能直接视为当前 HEAD 的可复现产物。

deploy/install.sh

@@ -72,15 +72,15 @@ install_agent() {
     read -rp "请输入本节点名称 (默认: ${DEFAULT_NAME}): " AGENT_NAME
     AGENT_NAME=${AGENT_NAME:-${DEFAULT_NAME}}
 
-    read -rp "请输入 Cluster Secret (集群通信密钥): " CLUSTER_SECRET
+    read -rp "请输入 Agent 独立凭据 Token: " AGENT_TOKEN
-    while [ -z "$CLUSTER_SECRET" ]; do
+    while [ -z "$AGENT_TOKEN" ]; do
-        read -rp "Cluster Secret 不能为空，请重新输入: " CLUSTER_SECRET
+        read -rp "Agent Token 不能为空，请重新输入: " AGENT_TOKEN
     done
 
     cat << ENV > "${CONF_DIR}/agent.env"
 VPS_COMMANDER_HUB_WS_URL=${HUB_WS}
 VPS_COMMANDER_AGENT_NAME=${AGENT_NAME}
-VPS_COMMANDER_CLUSTER_SECRET=***
+VPS_COMMANDER_AGENT_TOKEN=${AGENT_TOKEN}
 ENV
     chmod 0600 "${CONF_DIR}/agent.env"
 
@@ -133,23 +133,19 @@ install_hub() {
     read -rp "请输入监听端口 (默认 9521): " HUB_PORT
     HUB_PORT=${HUB_PORT:-9521}
 
-    GEN_API_KEY=*** -c 24 /dev/urandom | xxd -p)
+    GEN_API_KEY=$(head -c 24 /dev/urandom | xxd -p)
-    GEN_SECRET=*** -c 24 /dev/urandom | xxd -p)
     GEN_PASS=$(head -c 16 /dev/urandom | xxd -p)
 
     read -rp "请输入 API Key (默认随机生成): " API_KEY
-    API_KEY=***
+    API_KEY=${API_KEY:-$GEN_API_KEY}
-
-    read -rp "请输入 Cluster Secret (默认随机生成): " CLUSTER_SECRET
-    CLUSTER_SECRET=${CLUS…RET}
 
     read -rp "请输入 Web 管理面板密码 (默认随机生成): " WEB_PASS
     WEB_PASS=${WEB_PASS:-$GEN_PASS}
 
     cat << ENV > "${CONF_DIR}/hub.env"
-VPS_COMMANDER_API_KEY=***
+VPS_COMMANDER_API_KEY=${API_KEY}
-VPS_COMMANDER_CLUSTER_SECRET=***
+VPS_COMMANDER_WEB_PASSWORD=${WEB_PASS}
-VPS_COMMANDER_WEB_PASSWORD=***
+ENV
 ENV
     chmod 0600 "${CONF_DIR}/hub.env"
 
@@ -185,7 +181,6 @@ SVC
         echo -e "\n================== Hub 配置凭据 =================="
         echo -e "监听地址: 127.0.0.1:${HUB_PORT}"
         echo -e "API Key: ${API_KEY}"
-        echo -e "Cluster Secret: ${CLUSTER_SECRET}"
         echo -e "Web 面板密码: ${WEB_PASS}"
         echo -e "==================================================\n"
         warn "请妥善保管上述凭据，反代请将域名反代至 127.0.0.1:${HUB_PORT}"

docs/MCP_INTEGRATION.md

@@ -162,7 +162,31 @@ API Key 不应提交到 Git 仓库。
 
 ---
 
-## 七、Agent MCP
+## 七、一键安装与升级
+
+### 7.1 一键安装
+
+仓库已经提供统一安装脚本，支持 Linux `amd64` 与 `arm64`，安装时自动识别架构并从 GitHub Release 获取对应二进制。
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/kyaring/vps-commander/main/deploy/install.sh | sudo bash
+```
+
+脚本会进入交互式安装流程，可选择 Hub 或 Agent。生产环境使用时，Agent 应使用独立设备凭据，不应重新启用全局 Shared Secret。
+
+### 7.2 一键升级 Agent
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/kyaring/vps-commander/main/deploy/upgrade-agent.sh | sudo bash
+```
+
+升级采用临时文件下载 → 基础完整性检查 → 旧二进制备份 → 原子替换 → systemd 重启 → 健康检查；启动失败时自动回滚旧版本。
+
+> Hub 的生产升级建议继续采用滚动发布：先完成 Release 与构建校验，再替换 Hub，确认节点重新上线后再继续后续节点。避免把 Hub 升级做成无保护的“一键重启”。
+
+---
+
+## 八、Agent MCP
 
 Hub 可以发现远程 Agent 暴露的 MCP Service。
 

internal/api/api.go

@@ -49,6 +49,7 @@ type Server struct {
 	AdminToken    string
 	ExecLimiter   chan struct{}
 	SearchLimiter chan struct{}
+	LocalSessions *executor.SessionManager
 }
 
 const (
@@ -782,9 +783,13 @@ func (s *Server) processSession(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 	var req struct {
-		Device, SessionID, Command, Workdir, Data string
+		Device       string `json:"device"`
-		Force                                     bool
+		SessionID    string `json:"session_id"`
-		RingCapacity                              int `json:"ring_capacity"`
+		Command      string `json:"command"`
+		Workdir      string `json:"workdir"`
+		Data         string `json:"data"`
+		Force        bool   `json:"force"`
+		RingCapacity int    `json:"ring_capacity"`
 	}
 	if err := json.NewDecoder(http.MaxBytesReader(w, r.Body, 256*1024)).Decode(&req); err != nil {
 		http.Error(w, "bad json", 400)
@@ -796,38 +801,106 @@ func (s *Server) processSession(w http.ResponseWriter, r *http.Request) {
 	if !s.requireSecurity(w, r, req.Device, "exec", req.SessionID) {
 		return
 	}
-	if s.Cluster == nil {
-		http.Error(w, "cluster unavailable", 503)
-		return
-	}
 	ctx, cancel := context.WithTimeout(r.Context(), 30*time.Second)
 	defer cancel()
 	action := r.URL.Query().Get("action")
+	owner := sessionOwner(r)
 	var result any
 	var err error
-	switch action {
+	if s.isRemote(req.Device) {
-	case "start":
+		if s.Cluster == nil || !s.Cluster.Online(req.Device) {
-		if req.SessionID == "" {
+			http.Error(w, "device offline", 409)
-			req.SessionID, err = newSessionID()
+			return
-			if err != nil {
+		}
-				http.Error(w, "session id generation failed", 500)
+		switch action {
-				return
+		case "start":
+			if req.SessionID == "" {
+				req.SessionID, err = newSessionID()
+				if err != nil {
+					http.Error(w, "session id generation failed", 500)
+					return
+				}
 			}
+			result, err = s.Cluster.StartProcess(ctx, req.Device, cluster.StartProcessPayload{Command: req.Command, Workdir: req.Workdir, SessionID: req.SessionID, Owner: owner, RingCapacity: req.RingCapacity})
+		case "read":
+			result, err = s.Cluster.ReadProcessOutput(ctx, req.Device, req.SessionID, owner)
+		case "input":
+			err = s.Cluster.InteractProcess(ctx, req.Device, req.SessionID, req.Data, owner)
+			result = map[string]any{"ok": true}
+		case "stop":
+			err = s.Cluster.ForceTerminate(ctx, req.Device, req.SessionID, owner)
+			result = map[string]any{"ok": true}
+		case "list":
+			result, err = s.Cluster.ListSessions(ctx, req.Device)
+		default:
+			http.Error(w, "unknown action", 400)
+			return
+		}
+	} else {
+		if s.LocalSessions == nil {
+			http.Error(w, "local session manager unavailable", 503)
+			return
+		}
+		switch action {
+		case "start":
+			if req.SessionID == "" {
+				req.SessionID, err = newSessionID()
+				if err != nil {
+					http.Error(w, "session id generation failed", 500)
+					return
+				}
+			}
+			var sess *executor.Session
+			sess, err = s.LocalSessions.Start(ctx, req.SessionID, req.Command, req.Workdir, owner, req.RingCapacity)
+			if err == nil {
+				result = map[string]any{"session_id": sess.ID, "started_at": sess.StartedAt.Unix()}
+			}
+		case "read":
+			var sess *executor.Session
+			sess, ok := s.LocalSessions.Get(req.SessionID)
+			if !ok {
+				err = fmt.Errorf("session not found")
+				break
+			}
+			if !sess.Authorized(owner) {
+				err = fmt.Errorf("session ownership denied")
+				break
+			}
+			code, done, _ := sess.Status()
+			stdout, stderr := sess.Output()
+			result = cluster.ProcessOutputPayload{SessionID: req.SessionID, Stdout: stdout, Stderr: stderr, ExitCode: code, Running: !done}
+		case "input":
+			var sess *executor.Session
+			sess, ok := s.LocalSessions.Get(req.SessionID)
+			if !ok {
+				err = fmt.Errorf("session not found")
+				break
+			}
+			if !sess.Authorized(owner) {
+				err = fmt.Errorf("session ownership denied")
+				break
+			}
+			err = sess.Stdin([]byte(req.Data))
+			result = map[string]any{"ok": true}
+		case "stop":
+			var sess *executor.Session
+			sess, ok := s.LocalSessions.Get(req.SessionID)
+			if !ok {
+				err = fmt.Errorf("session not found")
+				break
+			}
+			if !sess.Authorized(owner) {
+				err = fmt.Errorf("session ownership denied")
+				break
+			}
+			err = s.LocalSessions.Stop(req.SessionID, true)
+			result = map[string]any{"ok": true}
+		case "list":
+			result = s.LocalSessions.List()
+		default:
+			http.Error(w, "unknown action", 400)
+			return
 		}
-		result, err = s.Cluster.StartProcess(ctx, req.Device, cluster.StartProcessPayload{Command: req.Command, Workdir: req.Workdir, SessionID: req.SessionID, Owner: sessionOwner(r), RingCapacity: req.RingCapacity})
-	case "read":
-		result, err = s.Cluster.ReadProcessOutput(ctx, req.Device, req.SessionID, sessionOwner(r))
-	case "input":
-		err = s.Cluster.InteractProcess(ctx, req.Device, req.SessionID, req.Data, sessionOwner(r))
-		result = map[string]any{"ok": true}
-	case "stop":
-		err = s.Cluster.ForceTerminate(ctx, req.Device, req.SessionID, sessionOwner(r))
-		result = map[string]any{"ok": true}
-	case "list":
-		result, err = s.Cluster.ListSessions(ctx, req.Device)
-	default:
-		http.Error(w, "unknown action", 400)
-		return
 	}
 	if err != nil {
 		http.Error(w, err.Error(), 409)

internal/mcp/mcp.go

@@ -286,6 +286,7 @@ func (s *Server) handleRequest(ctx context.Context, r *http.Request, req JSONRPC
 				InputSchema: InputSchema{Type: "object", Properties: map[string]PropertyDef{"device": {Type: "string", Description: "目标节点名称"}, "path": {Type: "string", Description: "目标文件路径"}, "old_text": {Type: "string", Description: "必须唯一匹配的原文本块"}, "new_text": {Type: "string", Description: "替换后的文本块"}}, Required: []string{"path", "old_text", "new_text"}},
 			},
 			{
+				Name:        "write_file",
 				Description: "向指定受控节点创建或覆写文件",
 				InputSchema: InputSchema{
 					Type: "object",

internal/mcp/mcp_test.go

@@ -82,6 +82,23 @@ func TestMCPInitializeAndListTools(t *testing.T) {
 	if !ok || len(tools) != 11 {
 		t.Fatalf("expected 11 tools, got %d", len(tools))
 	}
+	foundWriteFile := false
+	for _, raw := range tools {
+		tool, ok := raw.(map[string]any)
+		if !ok {
+			t.Fatalf("tool entry is not an object: %#v", raw)
+		}
+		name, _ := tool["name"].(string)
+		if name == "" {
+			t.Fatalf("tool entry has empty name: %#v", tool)
+		}
+		if name == "write_file" {
+			foundWriteFile = true
+		}
+	}
+	if !foundWriteFile {
+		t.Fatalf("write_file missing from tools/list")
+	}
 }
 
 func TestMCPCallTool(t *testing.T) {