release: unify upgrade and release pipeline

.github/workflows/release.yml

@@ -2,8 +2,6 @@ name: Release
 
 on:
   push:
-    branches:
-      - main
     tags:
       - 'v*'
 
@@ -20,49 +18,27 @@ jobs:
         with:
           fetch-depth: 0
 
-      - name: Determine Version Tag & Generate Notes
+      - name: Prepare Release Notes
         id: versioning
         run: |
-          PREV_TAG=$(git tag -l "v*" --sort=-v:refname | head -n1)
-          echo "Previous tag: $PREV_TAG"
-
-          if [[ "${{ github.ref }}" == refs/tags/v* ]]; then
           TAG="${GITHUB_REF#refs/tags/}"
-          else
+          git fetch --tags --force
-            if [ -z "$PREV_TAG" ]; then
+          PREV_TAG=$(git tag -l "v*" --sort=-v:refname | grep -Fxv "$TAG" | head -n1 || true)
-              TAG="v1.0.0"
+          echo "tag=$TAG" >> "$GITHUB_OUTPUT"
-            else
+          {
-              VER_NUM="${PREV_TAG#v}"
+            echo "### 🚀 What's Changed in ${TAG}"
-              IFS='.' read -r MAJOR MINOR PATCH <<< "$VER_NUM"
+            echo
-              PATCH=$((PATCH + 1))
-              TAG="v${MAJOR}.${MINOR}.${PATCH}"
-            fi
-            echo "Auto incremented patch version to $TAG"
-            
-            git config user.name "github-actions[bot]"
-            git config user.email "github-actions[bot]@users.noreply.github.com"
-            git tag "$TAG"
-            git push origin "$TAG"
-          fi
-          echo "tag=$TAG" >> $GITHUB_OUTPUT
-
-          # 生成详细的 Release Changelog 正文
-          cat << NOTES > release_notes.md
-          ### 🚀 What's Changed in ${TAG}
-
-          NOTES
-
             if [ -n "$PREV_TAG" ]; then
-            git log "${PREV_TAG}..HEAD" --pretty=format:"- %s (%h by @kyaring)" >> release_notes.md
+              git log "${PREV_TAG}..${TAG}" --pretty=format:"- %s (%h by @kyaring)"
             else
-            git log -n 10 --pretty=format:"- %s (%h by @kyaring)" >> release_notes.md
+              git log -n 10 --pretty=format:"- %s (%h by @kyaring)"
             fi
-
+            echo
-          echo "" >> release_notes.md
+            echo
-          echo "" >> release_notes.md
             if [ -n "$PREV_TAG" ]; then
-            echo "**Full Changelog**: https://github.com/${{ github.repository }}/compare/${PREV_TAG}...${TAG}" >> release_notes.md
+              echo "**Full Changelog**: https://github.com/${{ github.repository }}/compare/${PREV_TAG}...${TAG}"
             fi
+          } > release_notes.md
           cat release_notes.md
 
       - name: Set up Go
@@ -81,6 +57,9 @@ jobs:
           CGO_ENABLED=0 GOOS=linux GOARCH=arm64 go build -trimpath -ldflags "-s -w" -o dist/vps-commander-hub-linux-arm64 ./cmd/hub
           CGO_ENABLED=0 GOOS=linux GOARCH=arm64 go build -trimpath -ldflags "-s -w" -o dist/vps-commander-agent-linux-arm64 ./cmd/agent
 
+          # MCP stdio（与 Gitea 本地发布保持一致）
+          CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -trimpath -ldflags "-s -w" -o dist/vps-commander-mcp-stdio-linux-amd64 ./cmd/mcp-stdio
+
           # Checksums
           cd dist
           sha256sum * > checksums.txt

README.md

@@ -111,7 +111,7 @@ Tool Registry 首先确定操作风险：
 
 ## 🤖 当前 MCP 能力
 
-目前共 **11 个 MCP Tools**：
+目前共 **12 个 MCP Tools**：
 
 | Tool | Risk | 功能 |
 | :--- | :--- | :--- |

cmd/agent/main.go

@@ -152,6 +152,17 @@ func run(hub, name, token string, insecure bool) error {
 
 func handle(writeJSON func(cluster.Message) error, exec executor.Local, mcpRuntime *cluster.MCPRuntime, sessions *executor.SessionManager, msg cluster.Message) error {
 	switch msg.Action {
+	case "diagnostic_command":
+		var p executor.DiagnosticRequest
+		if err := decodePayload(msg.Payload, &p); err != nil {
+			return sendError(writeJSON, msg.ID, err)
+		}
+		v, err := executor.Diagnostic(context.Background(), p)
+		if err != nil {
+			return sendError(writeJSON, msg.ID, err)
+		}
+		return writeJSON(cluster.Message{ID: msg.ID, Status: "success", Payload: v})
+
 	case "mcp_list":
 		return writeJSON(cluster.Message{ID: msg.ID, Status: "success", Payload: mcpRuntime.List()})
 	case "mcp_test":

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

@@ -195,7 +195,7 @@ Agent 启动后主动连接 Hub，并在设备列表中显示为 `online`。
 
 本地 stdio 使用 `vps-commander-mcp-stdio`。
 
-当前共 11 个 MCP tools，详见 `docs/MCP_INTEGRATION.md`。
+当前共 12 个 MCP tools，详见 `docs/MCP_INTEGRATION.md`。
 
 ---
 

deploy/install.sh

@@ -8,6 +8,7 @@ REPO="kyaring/vps-commander"
 INSTALL_DIR="/opt/vps-commander"
 CONF_DIR="/etc/vps-commander"
 GITHUB_URL="https://github.com"
+API_URL="https://api.github.com"
 
 # 颜色输出
 RED='\033[0;31m'
@@ -37,13 +38,40 @@ command -v curl >/dev/null 2>&1 || (apt-get update && apt-get install -y curl ||
 
 # 获取最新版本 tag
 info "正在获取 VPS-Commander 最新版本信息..."
-LATEST_TAG=$(curl -fsSL -k "https://api.github.com/repos/${REPO}/releases/latest" 2>/dev/null | grep '"tag_name":' | head -n1 | sed -E 's/.*"([^"]+)".*/\1/')
+LATEST_TAG=$(curl -fsSL --proto '=https' --proto-redir '=https' --retry 3 --connect-timeout 15 --max-time 30 "${API_URL}/repos/${REPO}/releases/latest" | sed -n 's/^[[:space:]]*"tag_name": "\([^"]*\)".*/\1/p' | head -n1)
 if [ -z "$LATEST_TAG" ]; then
-    warn "无法通过 GitHub API 自动获取 Tag，回退至 v1.1.5"
+    error "无法从 GitHub 获取最新正式 Release，已停止安装；不会回退到旧版本"
-    LATEST_TAG="v1.1.5"
 fi
 info "检测到最新版本: ${LATEST_TAG} (${TARGET_ARCH})"
 
+download_verified() {
+    local url="$1" dest="$2" asset_name="$3"
+    local tmp checksum expected actual
+    tmp=$(mktemp "${dest}.tmp.XXXXXX") || error "无法创建临时下载文件: ${dest}"
+    rm -f "$tmp"
+    trap 'rm -f "${tmp}"' RETURN
+    info "正在下载: ${url}"
+    if ! curl -fL --proto '=https' --proto-redir '=https' --retry 3 --connect-timeout 15 --max-time 600 -o "$tmp" "$url"; then
+        rm -f "$tmp"
+        error "下载失败: ${url}"
+    fi
+    if [ ! -s "$tmp" ]; then
+        rm -f "$tmp"
+        error "下载结果为空: ${asset_name}"
+    fi
+    if command -v sha256sum >/dev/null 2>&1; then
+        checksum=$(curl -fsSL --proto '=https' --proto-redir '=https' --retry 3 --connect-timeout 15 --max-time 60 "${GITHUB_URL}/${REPO}/releases/download/${LATEST_TAG}/checksums.txt") || error "无法获取 Release 校验文件"
+        expected=$(printf '%s\n' "$checksum" | awk -v f="$asset_name" '$2 == f {print $1; exit}')
+        [ -n "$expected" ] || error "Release 校验文件中缺少 ${asset_name}"
+        actual=$(sha256sum "$tmp" | awk '{print $1}')
+        [ "$actual" = "$expected" ] || error "SHA256 校验失败: ${asset_name}"
+    else
+        error "系统缺少 sha256sum，无法安全校验 Release"
+    fi
+    mv -f "$tmp" "$dest" || error "无法安装下载文件到: ${dest}"
+    trap - RETURN
+}
+
 mkdir -p "$INSTALL_DIR" "$INSTALL_DIR/data" "$CONF_DIR"
 chmod 750 "$INSTALL_DIR" "$CONF_DIR"
 
@@ -60,8 +88,7 @@ install_agent() {
     BIN_NAME="vps-commander-agent-linux-${TARGET_ARCH}"
     DOWNLOAD_URL="${GITHUB_URL}/${REPO}/releases/download/${LATEST_TAG}/${BIN_NAME}"
 
-    info "正在下载 Agent: ${DOWNLOAD_URL}"
+    download_verified "${DOWNLOAD_URL}" "${INSTALL_DIR}/vps-commander-agent" "${BIN_NAME}"
-    curl -fsSL -k -o "${INSTALL_DIR}/vps-commander-agent" "${DOWNLOAD_URL}" || error "下载失败，请检查网络或 Release 是否存在"
     chmod +x "${INSTALL_DIR}/vps-commander-agent"
 
     echo -e "\n--- 配置 Agent 参数 ---"
@@ -125,16 +152,15 @@ install_hub() {
     BIN_NAME="vps-commander-hub-linux-${TARGET_ARCH}"
     DOWNLOAD_URL="${GITHUB_URL}/${REPO}/releases/download/${LATEST_TAG}/${BIN_NAME}"
 
-    info "正在下载 Hub: ${DOWNLOAD_URL}"
+    download_verified "${DOWNLOAD_URL}" "${INSTALL_DIR}/vps-commander-hub" "${BIN_NAME}"
-    curl -fsSL -k -o "${INSTALL_DIR}/vps-commander-hub" "${DOWNLOAD_URL}" || error "下载失败，请检查网络或 Release 是否存在"
     chmod +x "${INSTALL_DIR}/vps-commander-hub"
 
     echo -e "\n--- 配置 Hub 参数 ---"
     read -rp "请输入监听端口 (默认 9521): " HUB_PORT
     HUB_PORT=${HUB_PORT:-9521}
 
-    GEN_API_KEY=$(head -c 24 /dev/urandom | xxd -p)
+    GEN_API_KEY=$(od -An -N24 -tx1 /dev/urandom | tr -d ' \n')
-    GEN_PASS=$(head -c 16 /dev/urandom | xxd -p)
+    GEN_PASS=$(od -An -N16 -tx1 /dev/urandom | tr -d ' \n')
 
     read -rp "请输入 API Key (默认随机生成): " API_KEY
     API_KEY=${API_KEY:-$GEN_API_KEY}
@@ -145,7 +171,6 @@ install_hub() {
     cat << ENV > "${CONF_DIR}/hub.env"
 VPS_COMMANDER_API_KEY=${API_KEY}
 VPS_COMMANDER_WEB_PASSWORD=${WEB_PASS}
-ENV
 ENV
     chmod 0600 "${CONF_DIR}/hub.env"
 

deploy/upgrade-agent.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-set -e
+set -euo pipefail
 
 # VPS-Commander Agent 一键安全升级脚本
 # Repo: https://github.com/kyaring/vps-commander
@@ -7,28 +7,19 @@ set -e
 REPO="kyaring/vps-commander"
 INSTALL_DIR="/opt/vps-commander"
 GITHUB_URL="https://github.com"
+API_URL="https://api.github.com"
 
-# 颜色输出
+RED='\033[0;31m'; GREEN='\033[0;32m'; YELLOW='\033[1;33m'; BLUE='\033[0;34m'; NC='\033[0m'
-RED='\033[0;31m'
-GREEN='\033[0;32m'
-YELLOW='\033[1;33m'
-BLUE='\033[0;34m'
-NC='\033[0m'
-
 info() { echo -e "${BLUE}[INFO]${NC} $*"; }
 success() { echo -e "${GREEN}[SUCCESS]${NC} $*"; }
 warn() { echo -e "${YELLOW}[WARN]${NC} $*"; }
 error() { echo -e "${RED}[ERROR]${NC} $*"; exit 1; }
 
-# 检查 root 权限
 [[ $EUID -ne 0 ]] && error "必须使用 root 权限运行此脚本"
+[ -f "${INSTALL_DIR}/vps-commander-agent" ] || error "未检测到已安装的 Agent (${INSTALL_DIR}/vps-commander-agent)，请先使用 install.sh 完整安装。"
+command -v curl >/dev/null 2>&1 || error "系统缺少 curl"
+command -v sha256sum >/dev/null 2>&1 || error "系统缺少 sha256sum，无法安全校验 Release"
 
-# 检查是否安装过 agent
-if [ ! -f "${INSTALL_DIR}/vps-commander-agent" ]; then
-    error "未检测到已安装的 Agent (${INSTALL_DIR}/vps-commander-agent)，请先使用 install.sh 完整安装。"
-fi
-
-# 架构检测
 ARCH=$(uname -m)
 case "$ARCH" in
     x86_64|amd64) TARGET_ARCH="amd64" ;;
@@ -36,45 +27,48 @@ case "$ARCH" in
     *) error "暂不支持的系统架构: $ARCH" ;;
 esac
 
-info "正在获取最新 Release 版本信息..."
+info "正在获取最新正式 Release 版本信息..."
-LATEST_TAG=$(curl -fsSL -k "https://api.github.com/repos/${REPO}/releases/latest" 2>/dev/null | grep '"tag_name":' | head -n1 | sed -E 's/.*"([^"]+)".*/\1/')
+LATEST_TAG=$(curl -fsSL --proto '=https' --proto-redir '=https' --retry 3 --connect-timeout 15 --max-time 30 \
-if [ -z "$LATEST_TAG" ]; then
+    "${API_URL}/repos/${REPO}/releases/latest" |
-    warn "无法通过 GitHub API 自动获取 Tag，回退至 v1.1.5"
+    sed -n 's/^[[:space:]]*"tag_name": "\\([^"]*\\)".*/\\1/p' | head -n1)
-    LATEST_TAG="v1.1.5"
+[ -n "$LATEST_TAG" ] || error "无法从 GitHub 获取最新正式 Release，已停止升级；不会回退到旧版本"
-fi
 info "目标升级版本: ${LATEST_TAG} (${TARGET_ARCH})"
 
 BIN_NAME="vps-commander-agent-linux-${TARGET_ARCH}"
 DOWNLOAD_URL="${GITHUB_URL}/${REPO}/releases/download/${LATEST_TAG}/${BIN_NAME}"
-TMP_BIN="${INSTALL_DIR}/vps-commander-agent.tmp"
+CHECKSUM_URL="${GITHUB_URL}/${REPO}/releases/download/${LATEST_TAG}/checksums.txt"
+TMP_BIN=$(mktemp "${INSTALL_DIR}/vps-commander-agent.tmp.XXXXXX") || error "无法创建临时文件"
+TMP_SUM=$(mktemp "${INSTALL_DIR}/vps-commander-checksums.tmp.XXXXXX") || { rm -f "$TMP_BIN"; error "无法创建校验文件"; }
 BAK_BIN="${INSTALL_DIR}/vps-commander-agent.bak"
+cleanup() { rm -f "$TMP_BIN" "$TMP_SUM"; }
+trap cleanup EXIT
 
 info "正在下载新版本二进制文件..."
-curl -fsSL -k -o "${TMP_BIN}" "${DOWNLOAD_URL}" || error "下载失败，请检查网络或 Release 是否存在"
+curl -fL --proto '=https' --proto-redir '=https' --retry 3 --connect-timeout 15 --max-time 600 -o "$TMP_BIN" "$DOWNLOAD_URL" || error "下载失败: ${DOWNLOAD_URL}"
+[ -s "$TMP_BIN" ] || error "下载结果为空"
 
-# 完整性校验：文件大小不能小于 1MB
+info "正在校验 SHA256..."
-FILE_SIZE=$(stat -c%s "${TMP_BIN}" 2>/dev/null || stat -f%z "${TMP_BIN}" 2>/dev/null || echo 0)
+curl -fsSL --proto '=https' --proto-redir '=https' --retry 3 --connect-timeout 15 --max-time 60 -o "$TMP_SUM" "$CHECKSUM_URL" || error "无法获取 Release 校验文件"
-if [ "$FILE_SIZE" -lt 1000000 ]; then
+EXPECTED=$(awk -v f="$BIN_NAME" '$2 == f {print $1; exit}' "$TMP_SUM")
-    rm -f "${TMP_BIN}"
+[ -n "$EXPECTED" ] || error "Release 校验文件中缺少 ${BIN_NAME}"
-    error "下载的文件不完整或损坏 (大小: ${FILE_SIZE} 字节)，已终止升级"
+ACTUAL=$(sha256sum "$TMP_BIN" | awk '{print $1}')
-fi
+[ "$ACTUAL" = "$EXPECTED" ] || error "SHA256 校验失败: ${BIN_NAME}"
-
+info "SHA256 校验通过: ${ACTUAL}"
-chmod +x "${TMP_BIN}"
 
+chmod +x "$TMP_BIN"
 info "备份旧版本并原子替换..."
-cp -f "${INSTALL_DIR}/vps-commander-agent" "${BAK_BIN}" 2>/dev/null || true
+cp -f "${INSTALL_DIR}/vps-commander-agent" "$BAK_BIN" 2>/dev/null || true
-mv -f "${TMP_BIN}" "${INSTALL_DIR}/vps-commander-agent"
+mv -f "$TMP_BIN" "${INSTALL_DIR}/vps-commander-agent"
 
 info "重启 vps-commander-agent 服务..."
 systemctl restart vps-commander-agent
 sleep 2
-
 if systemctl is-active --quiet vps-commander-agent; then
-    success "Agent 成功平滑升级至 ${LATEST_TAG} 并已恢复运行！"
+    success "Agent 成功升级至 ${LATEST_TAG}，SHA256 已验证并恢复运行。"
-    rm -f "${BAK_BIN}"
+    rm -f "$BAK_BIN"
 else
     warn "服务启动异常，正在自动回滚原版本..."
-    mv -f "${BAK_BIN}" "${INSTALL_DIR}/vps-commander-agent"
+    mv -f "$BAK_BIN" "${INSTALL_DIR}/vps-commander-agent"
     systemctl restart vps-commander-agent
     error "升级失败，已安全回滚至上一版本，请查看日志: journalctl -u vps-commander-agent -n 20"
 fi

docs/ARCHITECTURE.md

@@ -88,6 +88,7 @@ Agent 返回结果后，Hub 完成审计并将结果返回 HTTP/MCP 调用方。
 | :--- | :--- |
 | Low | read_file、read_multiple_files、list_directory、file_info、search、list_processes |
 | Medium | edit_block、write_file、create_directory、move_file、mcp_call |
+| Low | diagnostic_command：严格白名单只读诊断（Docker、systemd、journal、网络监听、磁盘、内存、uptime） |
 | High | exec_command、start_process、interact_with_process、kill_process、force_terminate |
 
 ### 4.3 Policy Snapshot
@@ -121,7 +122,7 @@ kill / terminate 使用 Session 内部进程句柄，不接受客户端任意 PI
 
 ## 六、MCP 架构
 
-当前 MCP 共 11 个工具：
+当前 MCP 共 12 个工具：
 1. `list_devices`
 2. `exec_command`
 3. `read_file`
@@ -129,6 +130,8 @@ kill / terminate 使用 Session 内部进程句柄，不接受客户端任意 PI
 5. `create_directory`
 6. `move_file`
 7. `list_processes`
+8. `diagnostic_command`：严格白名单的只读系统诊断；
+
 8. `edit_block`
 9. `write_file`
 10. `list_agent_mcp`

docs/DEV_SPEC.md

@@ -86,7 +86,7 @@ Hub 根据 Credential 建立 Canonical Device Identity。
 Server version：`1.2.0`。
 Protocol Version：`2024-11-05`。
 
-当前工具共 11 个：
+当前工具共 12 个：
 `list_devices`、`exec_command`、`read_file`、`read_multiple_files`、`create_directory`、`move_file`、`list_processes`、`edit_block`、`write_file`、`list_agent_mcp`、`call_agent_mcp`。
 
 远程 transport：legacy HTTP + SSE。

docs/DOCUMENTATION_BASELINE_20261002.md

@@ -40,7 +40,7 @@ VPS-Commander 是自托管、多节点、AI Agent 友好的 Linux 运维控制
 
 ## 三、当前 MCP 基线
 
-11 个工具：
+12 个工具：
 `list_devices`、`exec_command`、`read_file`、`read_multiple_files`、`create_directory`、`move_file`、`list_processes`、`edit_block`、`write_file`、`list_agent_mcp`、`call_agent_mcp`。
 
 远程：legacy SSE。

docs/KNOWN_ISSUE_STREAMABLE_HTTP_20261002.md

@@ -0,0 +1,49 @@
+# 已知问题：MCP Streamable HTTP 传输不受支持（待排期）
+
+- **发现日期**：2026-10-02
+- **发现人**：审核专家 B（生产问题分析）
+- **状态**：待排期，未修复
+
+---
+
+## 现象
+
+Android 客户端使用 MCP Kotlin SDK 的 `StreamableHttpClientTransport` 连接 vps-commander，
+发送第一条消息（`initialize`）时失败：
+
+```
+io.modelcontextprotocol.kotlin.sdk.types.McpException: Error while sending message: Streamable HTTP error:
+Caused by: io.modelcontextprotocol.kotlin.sdk.client.StreamableHttpError: Streamable HTTP error:
+    at ...StreamableHttpClientTransport.performSend(...)
+```
+
+## 根因
+
+传输协议代际不匹配：
+
+| | 服务端 (vps-commander) | 客户端 (Kotlin SDK) |
+|---|---|---|
+| 协议 | SSE 传输（MCP 2024-11-05） | Streamable HTTP（MCP 2025-03-26） |
+| 端点 | `GET /mcp/sse` + `POST /mcp/message` | `POST /mcp`（单端点） |
+| 行为 | `HandleSSE` 非 GET 直接 405（`internal/mcp/mcp.go:120`） | POST 收到非 2xx 即抛 `StreamableHttpError` |
+
+服务端没有 `POST /mcp` 路由。客户端 POST 打到 `/mcp/sse` 得 405，打到 `/mcp` 得 404，
+两种情况都会触发该异常。SDK 的错误信息为空（未携带 HTTP 状态码），需抓包/curl 确认。
+
+## 验证
+
+```bash
+curl -i -X POST https://vpstool.kory.kdns.fr/mcp/sse \
+  -H "Content-Type: application/json" -d '{}'
+# 预期：405 method not allowed（坐实协议不匹配）
+```
+
+## 修复选项（待决策）
+
+1. **客户端改（快）**：Android 端改用 `SseClientTransport`，URL 指向 `/mcp/sse`，与服务端现状匹配。
+2. **服务端加（彻底）**：实现 Streamable HTTP（`POST /mcp`，MCP 2025-03-26），属新功能开发。
+
+## 备注
+
+- 与 2026-10-02 bug hunt 的 4 个 bug 无关，是独立的协议兼容性问题。
+- 决策前不要动生产端点。

docs/MCP_INTEGRATION.md

@@ -20,7 +20,7 @@ VPS-Commander 当前提供两种 MCP 接入模式：
 
 ---
 
-## 二、当前支持的 11 大 MCP Tools
+## 二、当前支持的 12 大 MCP Tools
 
 | Tool 名称 | 风险等级 | 参数/功能说明 |
 | :--- | :--- | :--- |
@@ -31,6 +31,7 @@ VPS-Commander 当前提供两种 MCP 接入模式：
 | `create_directory` | Medium | 创建目录 |
 | `move_file` | Medium | 移动/重命名文件 |
 | `list_processes` | Low | 查看进程 |
+| `diagnostic_command` | Low | 严格白名单只读诊断，不接受任意 Shell |
 | `edit_block` | Medium | 唯一匹配 + 原子写回 |
 | `write_file` | Medium | 创建或覆写文件 |
 | `list_agent_mcp` | Low | 查询 Agent MCP 服务 |
@@ -145,6 +146,12 @@ API Key 不应提交到 Git 仓库。
 ### 6.6 list_processes
 - `device` 可选。
 
+### 6.7 diagnostic_command
+- `device`、`action` 必填。
+- `action` 仅允许：`docker_ps`、`docker_logs`、`docker_inspect`、`systemctl_status`、`journalctl`、`ss_listen`、`df`、`free`、`uptime`。
+- 这是 Low 风险只读诊断通道，不接受任意 Shell；Medium 模式可使用，但 `exec_command` 仍保持 High。
+
+
 ### 6.7 edit_block
 - `device`、`path`、`old_text`、`new_text`。
 - `old_text` 必须唯一匹配。

docs/PROGRESS_TRACKING.md

@@ -28,7 +28,7 @@
 
 ## 二、MCP 当前能力
 
-当前共 11 个 Tools：
+当前共 12 个 Tools：
 1. `list_devices`
 2. `exec_command`
 3. `read_file`

internal/api/api.go

@@ -49,6 +49,7 @@ type Server struct {
 	AdminToken    string
 	ExecLimiter   chan struct{}
 	SearchLimiter chan struct{}
+	LocalSessions *executor.SessionManager
 }
 
 const (
@@ -782,8 +783,12 @@ 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"`
+		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 {
@@ -796,15 +801,17 @@ 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
+	if s.isRemote(req.Device) {
+		if s.Cluster == nil || !s.Cluster.Online(req.Device) {
+			http.Error(w, "device offline", 409)
+			return
+		}
 		switch action {
 		case "start":
 			if req.SessionID == "" {
@@ -814,14 +821,14 @@ func (s *Server) processSession(w http.ResponseWriter, r *http.Request) {
 					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})
+			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, sessionOwner(r))
+			result, err = s.Cluster.ReadProcessOutput(ctx, req.Device, req.SessionID, owner)
 		case "input":
-		err = s.Cluster.InteractProcess(ctx, req.Device, req.SessionID, req.Data, sessionOwner(r))
+			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, sessionOwner(r))
+			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)
@@ -829,6 +836,72 @@ func (s *Server) processSession(w http.ResponseWriter, r *http.Request) {
 			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(context.Background(), 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
+		}
+	}
 	if err != nil {
 		http.Error(w, err.Error(), 409)
 		return

internal/api/api_test.go

@@ -9,6 +9,7 @@ import (
 	"strings"
 	"sync"
 	"testing"
+	"time"
 
 	"github.com/wjyhk/vps-commander/internal/executor"
 	"github.com/wjyhk/vps-commander/internal/storage"
@@ -92,6 +93,38 @@ func TestSecurityEffectiveModeAndExecGate(t *testing.T) {
 	}
 }
 
+func TestProcessSessionLocalSnakeCaseAndLifecycle(t *testing.T) {
+	dir := t.TempDir()
+	store, err := storage.Open(filepath.Join(dir, "db.sqlite"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer store.DB.Close()
+	if err := store.SetGlobalSecurityMode("high"); err != nil {
+		t.Fatal(err)
+	}
+	s := &Server{Exec: executor.Local{MaxOutput: 1024 * 1024}, Store: store, LocalName: "local", LocalSessions: executor.NewSessionManager(0)}
+	if err := s.LoadSecurityPolicySnapshot(); err != nil {
+		t.Fatal(err)
+	}
+	req := httptest.NewRequest(http.MethodPost, "/api/v1/process/session?action=start", strings.NewReader(`{"device":"local","session_id":"session-test-001","command":"sleep 0.2; printf local-ok"}`))
+	w := httptest.NewRecorder()
+	s.processSession(w, req)
+	if w.Code != http.StatusOK {
+		t.Fatalf("start status=%d body=%s", w.Code, w.Body.String())
+	}
+	time.Sleep(1 * time.Second)
+	req = httptest.NewRequest(http.MethodPost, "/api/v1/process/session?action=read", strings.NewReader(`{"device":"local","session_id":"session-test-001"}`))
+	w = httptest.NewRecorder()
+	s.processSession(w, req)
+	if w.Code != http.StatusOK {
+		t.Fatalf("read status=%d body=%s", w.Code, w.Body.String())
+	}
+	if !strings.Contains(w.Body.String(), "local-ok") {
+		t.Fatalf("missing session output: %s", w.Body.String())
+	}
+}
+
 func TestEditBlockSecurityAndReplacement(t *testing.T) {
 	dir := t.TempDir()
 	store, err := storage.Open(filepath.Join(dir, "db.sqlite"))

internal/api/mcp_adapter.go

@@ -98,6 +98,33 @@ func (b *MCPBackend) ExecCommand(ctx context.Context, clientIP, device, command,
 	}, nil
 }
 
+func (b *MCPBackend) DiagnosticCommand(ctx context.Context, clientIP, device string, req executor.DiagnosticRequest) (any, error) {
+	if device == "" {
+		device = b.server.LocalName
+	}
+	if err := b.authorize(device, "diagnostic", clientIP); err != nil {
+		return nil, err
+	}
+	if req.Action == "" {
+		return nil, errors.New("diagnostic action required")
+	}
+	if b.server.isRemote(device) {
+		if b.server.Cluster == nil || !b.server.Cluster.Online(device) {
+			return nil, fmt.Errorf("device %s is offline", device)
+		}
+		res, err := b.server.Cluster.Diagnostic(ctx, device, req)
+		if err != nil {
+			return nil, err
+		}
+		return res, nil
+	}
+	res, err := executor.Diagnostic(ctx, req)
+	if err != nil {
+		return nil, err
+	}
+	return res, nil
+}
+
 func (b *MCPBackend) ReadFile(ctx context.Context, clientIP, device, path string, offset, limit int64) (any, error) {
 	if device == "" {
 		device = b.server.LocalName

internal/cluster/manager.go

@@ -13,6 +13,7 @@ import (
 	"time"
 
 	"github.com/gorilla/websocket"
+	"github.com/wjyhk/vps-commander/internal/executor"
 	"github.com/wjyhk/vps-commander/internal/security"
 	"github.com/wjyhk/vps-commander/internal/storage"
 	"github.com/wjyhk/vps-commander/internal/sysinfo"
@@ -464,6 +465,19 @@ func (m *Manager) Exec(ctx context.Context, name string, p ExecPayload) (Result,
 	return Result{msg.ExitCode, msg.Stdout, msg.Stderr, msg.DurationMS}, nil
 }
 
+func (m *Manager) Diagnostic(ctx context.Context, name string, req executor.DiagnosticRequest) (executor.DiagnosticResult, error) {
+	msg, err := m.call(ctx, name, "diagnostic_command", req)
+	if err != nil {
+		return executor.DiagnosticResult{}, err
+	}
+	b, _ := json.Marshal(msg.Payload)
+	var out executor.DiagnosticResult
+	if err := json.Unmarshal(b, &out); err != nil {
+		return out, err
+	}
+	return out, nil
+}
+
 func (m *Manager) ReadFile(ctx context.Context, name string, p FileReadPayload) (FileResult, error) {
 	msg, err := m.call(ctx, name, "file_read", p)
 	if err != nil {

internal/executor/diagnostic.go

@@ -0,0 +1,117 @@
+package executor
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os/exec"
+	"strconv"
+	"strings"
+	"time"
+)
+
+// DiagnosticRequest is a structured, read-only diagnostic operation. It is deliberately
+// not a shell command: every action maps to a fixed executable/argument set.
+type DiagnosticRequest struct {
+	Action string `json:"action"`
+	Target string `json:"target,omitempty"`
+	Lines  int    `json:"lines,omitempty"`
+}
+
+type DiagnosticResult struct {
+	Action     string `json:"action"`
+	Target     string `json:"target,omitempty"`
+	ExitCode   int    `json:"exit_code"`
+	Stdout     string `json:"stdout"`
+	Stderr     string `json:"stderr"`
+	DurationMS int64  `json:"duration_ms"`
+}
+
+func Diagnostic(ctx context.Context, req DiagnosticRequest) (DiagnosticResult, error) {
+	args, err := diagnosticArgs(req)
+	if err != nil {
+		return DiagnosticResult{}, err
+	}
+	if req.Lines <= 0 {
+		req.Lines = 100
+	}
+	if req.Lines > 500 {
+		req.Lines = 500
+	}
+	// docker logs is the only operation where a caller-controlled numeric limit is useful.
+	if req.Action == "docker_logs" {
+		args = []string{"logs", "--tail", strconv.Itoa(req.Lines), req.Target}
+	}
+
+	start := time.Now()
+	c, cancel := context.WithTimeout(ctx, 15*time.Second)
+	defer cancel()
+	cmd := exec.CommandContext(c, args[0], args[1:]...)
+	out, runErr := cmd.CombinedOutput()
+	const maxOutput = 256 * 1024
+	if len(out) > maxOutput {
+		out = append(out[:maxOutput], []byte("\n[output truncated at 256 KiB]\n")...)
+	}
+	code := 0
+	if cmd.ProcessState != nil {
+		code = cmd.ProcessState.ExitCode()
+	}
+	result := DiagnosticResult{Action: req.Action, Target: req.Target, ExitCode: code, Stdout: string(out), DurationMS: time.Since(start).Milliseconds()}
+	if runErr != nil && code == -1 {
+		return result, fmt.Errorf("diagnostic failed: %w", runErr)
+	}
+	return result, nil
+}
+
+func diagnosticArgs(req DiagnosticRequest) ([]string, error) {
+	target := strings.TrimSpace(req.Target)
+	switch req.Action {
+	case "docker_ps":
+		if target != "" {
+			return nil, errors.New("docker_ps does not accept target")
+		}
+		return []string{"docker", "ps", "--no-trunc"}, nil
+	case "docker_logs":
+		if target == "" || strings.ContainsAny(target, " \t\r\n;|&<>$`") {
+			return nil, errors.New("invalid docker container target")
+		}
+		return []string{"docker", "logs", "--tail", "100", target}, nil
+	case "docker_inspect":
+		if target == "" || strings.ContainsAny(target, " \t\r\n;|&<>$`") {
+			return nil, errors.New("invalid docker target")
+		}
+		return []string{"docker", "inspect", target}, nil
+	case "systemctl_status":
+		if target == "" || strings.ContainsAny(target, " \t\r\n;|&<>$`") {
+			return nil, errors.New("invalid systemd unit")
+		}
+		return []string{"systemctl", "status", "--no-pager", "--full", target}, nil
+	case "journalctl":
+		if target == "" || strings.ContainsAny(target, " \t\r\n;|&<>$`") {
+			return nil, errors.New("invalid journal unit")
+		}
+		return []string{"journalctl", "--no-pager", "-u", target, "-n", "100"}, nil
+	case "ss_listen":
+		if target != "" {
+			return nil, errors.New("ss_listen does not accept target")
+		}
+		return []string{"ss", "-lntp"}, nil
+	case "df":
+		if target != "" {
+			return nil, errors.New("df does not accept target")
+		}
+		return []string{"df", "-h"}, nil
+	case "free":
+		if target != "" {
+			return nil, errors.New("free does not accept target")
+		}
+		return []string{"free", "-h"}, nil
+	case "uptime":
+		if target != "" {
+			return nil, errors.New("uptime does not accept target")
+		}
+		return []string{"uptime"}, nil
+	default:
+		return nil, fmt.Errorf("unsupported diagnostic action: %s", req.Action)
+	}
+}

internal/executor/diagnostic_test.go

@@ -0,0 +1,24 @@
+package executor
+
+import (
+	"context"
+	"strings"
+	"testing"
+)
+
+func TestDiagnosticRejectsShellInjection(t *testing.T) {
+	_, err := Diagnostic(context.Background(), DiagnosticRequest{Action: "docker_logs", Target: "edgeever;rm -rf /"})
+	if err == nil || !strings.Contains(err.Error(), "invalid docker") {
+		t.Fatalf("expected target rejection, got %v", err)
+	}
+}
+
+func TestDiagnosticAllowsReadOnlyUptime(t *testing.T) {
+	got, err := Diagnostic(context.Background(), DiagnosticRequest{Action: "uptime"})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got.ExitCode != 0 || strings.TrimSpace(got.Stdout) == "" {
+		t.Fatalf("unexpected uptime result: %#v", got)
+	}
+}

internal/mcp/mcp.go

@@ -12,6 +12,7 @@ import (
 	"time"
 
 	"github.com/wjyhk/vps-commander/internal/auth"
+	"github.com/wjyhk/vps-commander/internal/executor"
 )
 
 // MCP Protocol / JSON-RPC 2.0 Types
@@ -77,6 +78,10 @@ type ActionBackend interface {
 	EditBlock(ctx context.Context, clientIP, device, path, oldText, newText string) (any, error)
 }
 
+type DiagnosticBackend interface {
+	DiagnosticCommand(ctx context.Context, clientIP, device string, req executor.DiagnosticRequest) (any, error)
+}
+
 type ExtendedBackend interface {
 	ReadMultipleFiles(ctx context.Context, clientIP, device string, paths []string, limit int64) (any, error)
 	CreateDirectory(ctx context.Context, clientIP, device, path string) (any, error)
@@ -280,6 +285,7 @@ func (s *Server) handleRequest(ctx context.Context, r *http.Request, req JSONRPC
 			{Name: "create_directory", Description: "创建目录", InputSchema: InputSchema{Type: "object", Properties: map[string]PropertyDef{"device": {Type: "string", Description: "目标设备"}, "path": {Type: "string", Description: "目录路径"}}, Required: []string{"path"}}},
 			{Name: "move_file", Description: "移动或重命名文件", InputSchema: InputSchema{Type: "object", Properties: map[string]PropertyDef{"device": {Type: "string", Description: "目标设备"}, "source": {Type: "string", Description: "源路径"}, "destination": {Type: "string", Description: "目标路径"}}, Required: []string{"source", "destination"}}},
 			{Name: "list_processes", Description: "列出受控节点当前进程", InputSchema: InputSchema{Type: "object", Properties: map[string]PropertyDef{"device": {Type: "string", Description: "目标设备"}}}},
+			{Name: "diagnostic_command", Description: "执行严格白名单的只读系统诊断，不接受任意 Shell", InputSchema: InputSchema{Type: "object", Properties: map[string]PropertyDef{"device": {Type: "string", Description: "目标设备"}, "action": {Type: "string", Description: "docker_ps|docker_logs|docker_inspect|systemctl_status|journalctl|ss_listen|df|free|uptime"}, "target": {Type: "string", Description: "容器名或 systemd unit（按 action 使用）"}, "lines": {Type: "integer", Description: "docker_logs 最大行数，1-500"}}, Required: []string{"action"}}},
 			{
 				Name:        "edit_block",
 				Description: "对指定文件执行唯一文本块的原子替换；old_text 必须恰好匹配一次",
@@ -430,6 +436,24 @@ func (s *Server) callTool(ctx context.Context, clientIP string, params CallToolP
 			return map[string]string{"error": err.Error()}, true
 		}
 		return res, false
+	case "diagnostic_command":
+		var a struct {
+			Device string `json:"device"`
+			Action string `json:"action"`
+			Target string `json:"target"`
+			Lines  int    `json:"lines"`
+		}
+		_ = json.Unmarshal(params.Arguments, &a)
+		b, ok := s.Backend.(DiagnosticBackend)
+		if !ok {
+			return map[string]string{"error": "diagnostic tools unavailable"}, true
+		}
+		res, err := b.DiagnosticCommand(ctx, clientIP, a.Device, executor.DiagnosticRequest{Action: a.Action, Target: a.Target, Lines: a.Lines})
+		if err != nil {
+			return map[string]string{"error": err.Error()}, true
+		}
+		return res, false
+
 	case "list_processes":
 		var a struct {
 			Device string `json:"device"`

internal/mcp/mcp_test.go

@@ -79,7 +79,7 @@ func TestMCPInitializeAndListTools(t *testing.T) {
 		t.Fatalf("expected map result")
 	}
 	tools, ok := resMap["tools"].([]any)
-	if !ok || len(tools) != 11 {
+	if !ok || len(tools) != 12 {
 		t.Fatalf("expected 11 tools, got %d", len(tools))
 	}
 	foundWriteFile := false

internal/security/registry.go

@@ -15,6 +15,7 @@ var registry = map[string]ToolSpec{
 	"start_search":            {Name: "start_search", RequiredRisk: RiskLow, Category: "search", ReadOnly: true},
 	"get_more_search_results": {Name: "get_more_search_results", RequiredRisk: RiskLow, Category: "search", ReadOnly: true},
 	"list_processes":          {Name: "list_processes", RequiredRisk: RiskLow, Category: "process", ReadOnly: true},
+	"diagnostic_command":      {Name: "diagnostic_command", RequiredRisk: RiskLow, Category: "diagnostic", ReadOnly: true},
 	"list_sessions":           {Name: "list_sessions", RequiredRisk: RiskLow, Category: "process", ReadOnly: true},
 	"read_process_output":     {Name: "read_process_output", RequiredRisk: RiskLow, Category: "process", ReadOnly: true},
 	"edit_block":              {Name: "edit_block", RequiredRisk: RiskMedium, Category: "file", ReadOnly: false},
@@ -31,7 +32,7 @@ var registry = map[string]ToolSpec{
 
 var actionTools = map[string]string{
 	"read": "read_file", "probe": "read_file", "write": "write_file",
-	"mcp": "mcp_call", "exec": "exec_command",
+	"mcp": "mcp_call", "exec": "exec_command", "diagnostic": "diagnostic_command",
 }
 
 func Lookup(name string) (ToolSpec, bool) {