feat(nodes): SSH bootstrap + housekeeping — install script, bundled binaries, auto-prune

- `containr nodes add <user@host>` mints an enroll token, SSHes once, runs the install script remotely; --print emits the one-liner - Public /api/agents/install.sh + /api/agents/download/{platform}; agent binaries built into the image under /agents - Agent-side `prune` (bounded docker system prune, volumes opt-in) and `system_df` commands - node_agents.auto_prune + health sweep enqueues daily prune; offline/online transitions notify admins - CLI nodes update/prune/commands + MCP tools (prune confirm-gated) - Usage page: install one-liner, per-node Prune + auto toggle Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-28 07:41:27 +00:00 · 2026-10-09 12:15:36 +02:00
1 parent 7547375cc2
commit 4848d1f6f0
@@ -6,6 +6,7 @@ import (
 	"crypto/sha256"
 	"crypto/subtle"
 	"database/sql"
+	_ "embed"
 	"encoding/hex"
 	"encoding/json"
 	"errors"
@@ -13,6 +14,7 @@ import (
 	"math"
 	"net/http"
 	"os"
+	"path/filepath"
 	"strings"
 	"time"

@@ -36,6 +38,7 @@ type NodeAgent struct {
 	Capabilities  AgentCapabilities      `json:"capabilities"`
 	Resources     NodeResources          `json:"resources"`
 	LastHeartbeat time.Time              `json:"last_heartbeat"`
+	AutoPrune     bool                   `json:"auto_prune"`
 	CreatedAt     time.Time              `json:"created_at"`
 	UpdatedAt     time.Time              `json:"updated_at"`
 	Metadata      map[string]interface{} `json:"metadata"`
@@ -234,6 +237,7 @@ func agentFromRow(row sqlcdb.NodeAgent) NodeAgent {
 		Port:      int(row.Port),
 		Status:    row.Status.String,
 		Version:   row.Version.String,
+		AutoPrune: row.AutoPrune,
 		Metadata:  map[string]interface{}{},
 	}
 	if row.LastHeartbeat.Valid {
@@ -489,6 +493,7 @@ func (h *NodeAgentHandler) UpdateAgent(c *gin.Context) {
 		Resources:     rawJSON(agent.Resources),
 		LastHeartbeat: sql.NullTime{Time: agent.LastHeartbeat, Valid: !agent.LastHeartbeat.IsZero()},
 		Metadata:      rawJSON(agent.Metadata),
+		AutoPrune:     agent.AutoPrune,
 	})
 	if err != nil {
 		c.JSON(http.StatusInternalServerError, gin.H{"error": "Failed to update agent"})
@@ -516,6 +521,7 @@ func applyAgentUpdates(agent *NodeAgent, updates map[string]interface{}) {
 	remarshal("capabilities", &agent.Capabilities)
 	remarshal("resources", &agent.Resources)
 	remarshal("metadata", &agent.Metadata)
+	remarshal("auto_prune", &agent.AutoPrune)
 }

 // DeleteAgent removes an agent
@@ -803,6 +809,33 @@ func (h *NodeAgentHandler) CreateContainer(c *gin.Context) {
 	c.JSON(http.StatusCreated, gin.H{"container": container})
 }

+// PruneAgent enqueues a bounded `docker system prune -af` command. Volumes
+// stay unless the caller explicitly opts in.
+func (h *NodeAgentHandler) PruneAgent(c *gin.Context) {
+	agentID := c.Param("id")
+	if _, err := h.q.GetAgent(c.Request.Context(), agentID); err != nil {
+		c.JSON(http.StatusNotFound, gin.H{"error": "Agent not found"})
+		return
+	}
+	var req struct {
+		Until   string `json:"until"`   // e.g. "168h" — only prune objects older than this
+		Volumes bool   `json:"volumes"` // destructive — off by default
+	}
+	_ = c.ShouldBindJSON(&req)
+
+	command, err := h.q.CreateCommand(c.Request.Context(), sqlcdb.CreateCommandParams{
+		ID:          uuid.New().String(),
+		Type:        "prune",
+		NodeAgentID: agentID,
+		Payload:     rawJSON(map[string]interface{}{"until": req.Until, "volumes": req.Volumes}),
+	})
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": "Failed to enqueue prune"})
+		return
+	}
+	c.JSON(http.StatusAccepted, gin.H{"command": command})
+}
+
 // ExecuteCommand executes a command on an agent
 func (h *NodeAgentHandler) ExecuteCommand(c *gin.Context) {
 	agentID := c.Param("id")
@@ -1214,9 +1247,45 @@ func (h *NodeAgentHandler) SetupPublicRoutes(router *gin.RouterGroup) {
 		agents.POST("/heartbeat", h.SendHeartbeat)
 		agents.GET("/:id/commands", h.GetPendingCommandsForAgent)
 		agents.POST("/:id/commands/:commandId/result", h.CompleteCommand)
+
+		// Bootstrap surface — the install script and agent binaries are
+		// public; the enroll token is the actual secret.
+		agents.GET("/install.sh", h.ServeInstallScript)
+		agents.GET("/download/:platform", h.ServeAgentBinary)
 	}
 }

+//go:embed assets/install-agent.sh
+var agentInstallScript string
+
+// ServeInstallScript returns the agent bootstrap script. The script
+// downloads the binary from this instance first, GH releases second.
+func (h *NodeAgentHandler) ServeInstallScript(c *gin.Context) {
+	c.Data(http.StatusOK, "text/x-sh", []byte(agentInstallScript))
+}
+
+// ServeAgentBinary streams a bundled agent binary. Images ship the
+// linux binaries under CONTAINR_AGENT_BIN_DIR (default /agents).
+func (h *NodeAgentHandler) ServeAgentBinary(c *gin.Context) {
+	platform := c.Param("platform")
+	if platform != "linux-amd64" && platform != "linux-arm64" {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "unsupported platform"})
+		return
+	}
+	dir := os.Getenv("CONTAINR_AGENT_BIN_DIR")
+	if dir == "" {
+		dir = "/agents"
+	}
+	path := filepath.Join(dir, "containr-agent-"+platform)
+	info, err := os.Stat(path)
+	if err != nil || info.IsDir() {
+		c.JSON(http.StatusNotFound, gin.H{"error": "no bundled binary for " + platform})
+		return
+	}
+	c.Header("Content-Disposition", `attachment; filename="containr-agent"`)
+	c.File(path)
+}
+
 // SetupAdminRoutes registers dashboard/control agent routes. Command
 // history and container details can leak sensitive output, so these stay
 // admin-only rather than joining the public read group.
@@ -1243,6 +1312,7 @@ func (h *NodeAgentHandler) SetupAdminRoutes(router *gin.RouterGroup) {
 		agents.DELETE("/:id/containers/:containerId", h.ContainerAction)

 		agents.GET("/:id/metrics", h.GetAgentMetrics)
+		agents.POST("/:id/prune", h.PruneAgent)
 		agents.POST("/:id/commands", h.ExecuteCommand)
 		agents.GET("/:id/commands", h.GetAgentCommands)
 		agents.GET("/:id/commands/:commandId", h.GetCommandStatus)
@@ -0,0 +1,82 @@
+#!/usr/bin/env bash
+# Containr node agent installer.
+#   curl -fsSL <api>/api/agents/install.sh | bash -s -- --url <api> --token <enroll-token>
+#
+# One-shot: downloads the agent binary from the Containr instance (or GH
+# releases as fallback), writes a systemd unit, starts it. SSH is never
+# needed again — the agent heartbeats and polls commands outbound.
+set -euo pipefail
+
+API_URL=""
+TOKEN=""
+AGENT_NAME=""
+VERSION=""
+
+while [ $# -gt 0 ]; do
+  case "$1" in
+    --url) API_URL="$2"; shift 2 ;;
+    --token) TOKEN="$2"; shift 2 ;;
+    --name) AGENT_NAME="$2"; shift 2 ;;
+    --version) VERSION="$2"; shift 2 ;;
+    *) echo "unknown flag: $1" >&2; exit 2 ;;
+  esac
+done
+
+[ -n "$API_URL" ] || { echo "--url is required" >&2; exit 2; }
+[ -n "$TOKEN" ] || { echo "--token is required (create one: containr nodes tokens create)" >&2; exit 2; }
+API_URL="${API_URL%/}"
+API_URL="${API_URL%/api/v1}"
+API_URL="${API_URL%/api}"
+
+info() { printf '\033[1;34m==>\033[0m %s\n' "$*"; }
+err()  { printf '\033[1;31mError:\033[0m %s\n' "$*" >&2; }
+
+[ "$(id -u)" = "0" ] || { err "run as root (sudo bash -s -- --url … --token …)"; exit 1; }
+command -v docker >/dev/null 2>&1 || { err "docker not found"; exit 1; }
+command -v curl >/dev/null 2>&1 || { err "curl not found"; exit 1; }
+
+ARCH="$(uname -m)"
+case "$ARCH" in
+  x86_64|amd64) ARCH=amd64 ;;
+  aarch64|arm64) ARCH=arm64 ;;
+  *) err "unsupported architecture: $ARCH"; exit 1 ;;
+esac
+
+BIN=/usr/local/bin/containr-agent
+info "downloading containr-agent (linux/$ARCH)"
+if ! curl -fsSL "$API_URL/api/agents/download/linux-$ARCH" -o "$BIN" 2>/dev/null; then
+  info "instance has no bundled binary — trying GitHub releases"
+  REF="${VERSION:-latest}"
+  if [ "$REF" = "latest" ]; then
+    DL="https://github.com/Dvorinka/Containr/releases/latest/download/containr-agent-linux-$ARCH"
+  else
+    DL="https://github.com/Dvorinka/Containr/releases/download/$REF/containr-agent-linux-$ARCH"
+  fi
+  curl -fsSL "$DL" -o "$BIN" || { err "agent download failed"; exit 1; }
+fi
+chmod +x "$BIN"
+
+UNIT=/etc/systemd/system/containr-agent.service
+info "writing systemd unit"
+cat > "$UNIT" <<UNIT
+[Unit]
+Description=Containr node agent
+After=docker.service network-online.target
+Wants=network-online.target
+Requires=docker.service
+
+[Service]
+Environment=CONTAINR_API_URL=$API_URL
+Environment=CONTAINR_AGENT_AUTH_TOKEN=$TOKEN
+Environment=CONTAINR_AGENT_NAME=${AGENT_NAME:-$(hostname)}
+Restart=always
+RestartSec=5
+ExecStart=$BIN
+
+[Install]
+WantedBy=multi-user.target
+UNIT
+
+systemctl daemon-reload
+systemctl enable --now containr-agent
+info "agent installed and started — it should appear in Containr within ~15s"
@@ -7,6 +7,7 @@ package api

 import (
 	"containr/internal/database"
+	"containr/internal/database/sqlcdb"
 	"context"
 	"encoding/json"
 	"fmt"
@@ -61,26 +62,28 @@ func StartAgentHealthSweep(ctx context.Context, db *database.DB) {
 	}()
 }

+type agentHealthRow struct {
+	id        string
+	name      string
+	status    string
+	stale     bool
+	autoPrune bool
+}
+
 func reconcileAgentHealth(db *database.DB, staleAfter time.Duration) {
 	cutoff := time.Now().Add(-staleAfter)
-	type agentRow struct {
-		id     string
-		name   string
-		status string
-		stale  bool
-	}
-	var agents []agentRow
+	var agents []agentHealthRow
 	rows, err := db.Query(
 		`SELECT id, COALESCE(name, hostname, id::text), COALESCE(status, ''),
-		        COALESCE(last_heartbeat < $1, TRUE)
+		        COALESCE(last_heartbeat < $1, TRUE), auto_prune
 		 FROM node_agents`, cutoff)
 	if err != nil {
 		log.Printf("containr: agent health sweep: %v", err)
 		return
 	}
 	for rows.Next() {
-		var a agentRow
-		if err := rows.Scan(&a.id, &a.name, &a.status, &a.stale); err == nil {
+		var a agentHealthRow
+		if err := rows.Scan(&a.id, &a.name, &a.status, &a.stale, &a.autoPrune); err == nil {
 			agents = append(agents, a)
 		}
 	}
@@ -104,6 +107,32 @@ func reconcileAgentHealth(db *database.DB, staleAfter time.Duration) {
 				fmt.Sprintf("Agent %s resumed heartbeating.", a.name), "agent", a.id)
 		}
 	}
+
+	scheduleAutoPrune(db, agents)
+}
+
+// scheduleAutoPrune enqueues a `prune` command once per day for agents
+// with auto_prune enabled. Disk pressure is the most common small-VPS
+// failure — this is the dflow setServerAutoCleanup analog.
+func scheduleAutoPrune(db *database.DB, agents []agentHealthRow) {
+	q := sqlcdb.New(db.DB)
+	for _, a := range agents {
+		if !a.autoPrune || a.stale {
+			continue
+		}
+		last, err := q.GetLastAgentCommandByType(context.Background(),
+			sqlcdb.GetLastAgentCommandByTypeParams{NodeAgentID: a.id, Type: "prune"})
+		if err == nil && last.CreatedAt.Valid && time.Since(last.CreatedAt.Time) < 24*time.Hour {
+			continue
+		}
+		if _, err := q.CreateCommand(context.Background(), sqlcdb.CreateCommandParams{
+			ID:          uuid.New().String(),
+			Type:        "prune",
+			NodeAgentID: a.id,
+		}); err != nil {
+			log.Printf("containr: auto-prune enqueue failed for agent %s: %v", a.id, err)
+		}
+	}
 }

 // StartUpgradeCheck polls GitHub for the latest release once a day and