felhom-controller/controller/internal/stacks/infra.go

package stacks

import (
	"fmt"
	"os"
	"os/exec"
	"path/filepath"
	"strings"

	"gitea.dooplex.hu/admin/felhom-controller/internal/infra"
)

const traefikNetwork = "traefik-public"

// EnsureBaseStack renders and deploys the base-infrastructure stacks (traefik, cloudflared,
// filebrowser) the controller needs for routing + external access. It is:
//   - single-flight: fired both at first boot and on every health tick; a TryLock ensures two
//     invocations never race on the same stack dir / run concurrent `compose up` on the same stack.
//   - idempotent: each stack is skipped when its container is already running, so the healthy-state
//     re-run is a cheap 3× `docker inspect` no-op.
//   - non-fatal by contract: returns a joined error for the caller to LOG; it must never crash the
//     controller. cloudflared is only deployed when a tunnel token is configured (LAN-only nodes
//     legitimately run without it — see the dynamic protected set in monitor.EffectiveProtected).
//
// Deploy order is load-bearing: traefik-public network → traefik → cloudflared → filebrowser (the
// composes declare the network `external: true`, so it must exist first).
func (m *Manager) EnsureBaseStack() error {
	if !m.infraMu.TryLock() {
		m.logger.Printf("[INFO] [infra] EnsureBaseStack already in progress — skipping this invocation")
		return nil
	}
	defer m.infraMu.Unlock()

	if err := m.ensureTraefikNetwork(); err != nil {
		return fmt.Errorf("base-infra: %w", err) // without the network, every stack `up` fails
	}

	base := m.cfg.Paths.StacksDir
	traefikDir := filepath.Join(base, "traefik")
	var errs []string

	if err := m.ensureTraefik(traefikDir); err != nil {
		errs = append(errs, fmt.Sprintf("traefik: %v", err))
	}

	// Wire the controller's OWN dashboard route into traefik. Unlike filebrowser (which self-registers
	// via Docker labels + network membership baked into its compose), the controller is started by the
	// golden bootstrap before traefik-public exists and the v2 bootstrap carries no domain — so it can't
	// self-label. We do it here, post-pull, where the domain is known: drop a file-provider route and
	// join the controller to traefik-public so traefik can resolve felhom-controller:8080.
	if err := m.wireController(traefikDir); err != nil {
		errs = append(errs, fmt.Sprintf("controller-route: %v", err))
	}

	if m.cfg.Infrastructure.CFTunnelToken != "" {
		if err := m.ensureCloudflared(filepath.Join(base, "cloudflared")); err != nil {
			errs = append(errs, fmt.Sprintf("cloudflared: %v", err))
		}
	} else {
		m.logger.Printf("[INFO] [infra] cloudflared skipped — no cf_tunnel_token configured (LAN-only node)")
	}

	if err := m.ensureFileBrowser(filepath.Join(base, "filebrowser")); err != nil {
		errs = append(errs, fmt.Sprintf("filebrowser: %v", err))
	}

	if len(errs) > 0 {
		return fmt.Errorf("base-infra bring-up: %s", strings.Join(errs, "; "))
	}
	return nil
}

func (m *Manager) ensureTraefik(dir string) error {
	if containerRunning("traefik") {
		return nil
	}
	m.logger.Printf("[INFO] [infra] deploying traefik → %s", dir)
	if err := os.MkdirAll(filepath.Join(dir, "dynamic"), 0o755); err != nil {
		return fmt.Errorf("mkdir dynamic: %w", err)
	}
	if err := os.MkdirAll(filepath.Join(dir, "certs"), 0o755); err != nil {
		return fmt.Errorf("mkdir certs: %w", err)
	}
	// acme.json must exist as a 0600 file before traefik starts (it writes issued certs into it).
	acme := filepath.Join(dir, "acme.json")
	if _, err := os.Stat(acme); os.IsNotExist(err) {
		if err := os.WriteFile(acme, []byte{}, 0o600); err != nil {
			return fmt.Errorf("create acme.json: %w", err)
		}
	}
	if err := os.Chmod(acme, 0o600); err != nil {
		return fmt.Errorf("chmod acme.json: %w", err)
	}
	files, err := infra.RenderTraefik(infra.TraefikData{
		ACMEEmail:  m.cfg.Customer.Email,
		CFAPIToken: m.cfg.Infrastructure.CFAPIToken,
	})
	if err != nil {
		return err
	}
	if err := writeInfraFiles(dir, files); err != nil {
		return err
	}
	return m.composeUp(dir)
}

func (m *Manager) ensureCloudflared(dir string) error {
	if containerRunning("cloudflared") {
		return nil
	}
	m.logger.Printf("[INFO] [infra] deploying cloudflared → %s", dir)
	files, err := infra.RenderCloudflared(infra.CloudflaredData{CFTunnelToken: m.cfg.Infrastructure.CFTunnelToken})
	if err != nil {
		return err
	}
	if err := writeInfraFiles(dir, files); err != nil {
		return err
	}
	return m.composeUp(dir)
}

func (m *Manager) ensureFileBrowser(dir string) error {
	if containerRunning("filebrowser") {
		return nil
	}
	composePath := filepath.Join(dir, "docker-compose.yml")
	if _, err := os.Stat(composePath); err == nil {
		// Already provisioned but not running — bring it up WITHOUT regenerating, so the storage
		// mounts that web.SyncFileBrowserMounts manages are preserved. Just `compose up -d`.
		m.logger.Printf("[INFO] [infra] filebrowser compose exists — starting without regenerating")
		return m.composeUp(dir)
	}
	m.logger.Printf("[INFO] [infra] deploying filebrowser → %s", dir)
	if err := os.MkdirAll(dir, 0o755); err != nil {
		return fmt.Errorf("mkdir: %w", err)
	}
	// Initial render: no storage mounts yet (web.SyncFileBrowserMounts fills them in on the first
	// storage-path change and owns all later regeneration).
	compose := infra.RenderFileBrowserCompose(m.cfg.Customer.Domain, nil)
	config := infra.RenderFileBrowserConfig(nil)
	if err := os.WriteFile(composePath, []byte(compose), 0o644); err != nil {
		return fmt.Errorf("write docker-compose.yml: %w", err)
	}
	if err := os.WriteFile(filepath.Join(dir, "config.yaml"), []byte(config), 0o644); err != nil {
		return fmt.Errorf("write config.yaml: %w", err)
	}
	return m.composeUp(dir)
}

// controllerContainer is the fixed name of the in-guest controller container (set by the golden
// bootstrap `docker run --name`). traefik resolves it by this name once both share traefik-public.
const controllerContainer = "felhom-controller"

// wireController makes the controller dashboard reachable through traefik: it writes the file-provider
// route (Host(felhom.<domain>) → http://felhom-controller:8080) and connects the controller container
// to traefik-public. Both are idempotent — the route is written only when its content changes (so the
// traefik file watcher doesn't reload every health tick), and the network connect is skipped when the
// controller is already attached. Domain is required (it comes from the hub pull); a missing domain is
// a no-op (logged) rather than an error.
func (m *Manager) wireController(traefikDir string) error {
	domain := m.cfg.Customer.Domain
	if domain == "" {
		m.logger.Printf("[WARN] [infra] controller route skipped — no customer domain configured")
		return nil
	}

	dynDir := filepath.Join(traefikDir, "dynamic")
	if err := os.MkdirAll(dynDir, 0o755); err != nil {
		return fmt.Errorf("mkdir dynamic: %w", err)
	}
	routePath := filepath.Join(dynDir, "controller.yml")
	want := infra.RenderControllerRoute(domain)
	if cur, err := os.ReadFile(routePath); err != nil || string(cur) != want {
		if err := os.WriteFile(routePath, []byte(want), 0o644); err != nil {
			return fmt.Errorf("write controller route: %w", err)
		}
		m.logger.Printf("[INFO] [infra] wrote controller route → %s (Host felhom.%s → felhom-controller:8080)", routePath, domain)
	}

	if !containerOnNetwork(controllerContainer, traefikNetwork) {
		out, err := exec.Command("docker", "network", "connect", traefikNetwork, controllerContainer).CombinedOutput()
		if err != nil && !strings.Contains(string(out), "already exists") {
			return fmt.Errorf("network connect %s: %s: %w", controllerContainer, strings.TrimSpace(string(out)), err)
		}
		m.logger.Printf("[INFO] [infra] connected %s to %s", controllerContainer, traefikNetwork)
	}
	return nil
}

// containerOnNetwork reports whether the named container is attached to the given docker network.
func containerOnNetwork(name, network string) bool {
	out, err := exec.Command("docker", "inspect", "--format",
		fmt.Sprintf("{{index .NetworkSettings.Networks %q}}", network), name).Output()
	if err != nil {
		return false
	}
	s := strings.TrimSpace(string(out))
	return s != "" && s != "<no value>"
}

// ensureTraefikNetwork creates the external traefik-public docker network if absent (idempotent;
// tolerates a create/inspect race). Uses the docker CLI directly — it's a network op, not compose.
func (m *Manager) ensureTraefikNetwork() error {
	if exec.Command("docker", "network", "inspect", traefikNetwork).Run() == nil {
		return nil
	}
	m.logger.Printf("[INFO] [infra] creating docker network %s", traefikNetwork)
	out, err := exec.Command("docker", "network", "create", traefikNetwork).CombinedOutput()
	if err != nil {
		// Tolerate a race where another actor created it between our inspect and create.
		if exec.Command("docker", "network", "inspect", traefikNetwork).Run() == nil {
			return nil
		}
		return fmt.Errorf("network create %s: %s: %w", traefikNetwork, strings.TrimSpace(string(out)), err)
	}
	return nil
}

// composeUp runs `docker compose up -d` in dir (DOMAIN injected by composeExecWithEnv).
func (m *Manager) composeUp(dir string) error {
	out, err := m.composeExecWithEnv(dir, nil, "up", "-d")
	if err != nil {
		return fmt.Errorf("compose up: %s: %w", truncateStr(strings.TrimSpace(out), 300), err)
	}
	return nil
}

// writeInfraFiles writes each rendered file at its required mode (enforced via Chmod so an existing
// file — e.g. a re-rendered .env — keeps 0600 even though WriteFile only honors mode on create).
func writeInfraFiles(dir string, files map[string]infra.FileSpec) error {
	if err := os.MkdirAll(dir, 0o755); err != nil {
		return fmt.Errorf("mkdir: %w", err)
	}
	for name, spec := range files {
		p := filepath.Join(dir, name)
		if err := os.WriteFile(p, []byte(spec.Content), os.FileMode(spec.Mode)); err != nil {
			return fmt.Errorf("write %s: %w", name, err)
		}
		if err := os.Chmod(p, os.FileMode(spec.Mode)); err != nil {
			return fmt.Errorf("chmod %s: %w", name, err)
		}
	}
	return nil
}

// containerRunning reports whether a container with the given name is currently running. It asks the
// daemon directly (works before the stack dir exists), mirroring monitor.checkProtectedContainers.
func containerRunning(name string) bool {
	out, err := exec.Command("docker", "inspect", "--format", "{{.State.Running}}", name).Output()
	if err != nil {
		return false
	}
	return strings.TrimSpace(string(out)) == "true"
}