mesh-host/internal/profile/detectors.go

package profile

import (
	"context"
	"fmt"
	"os"
	"strings"
)

// Named capabilities. Constants rather than strings at the call site, because a capability
// nothing declares is a capability nothing can require, and a typo would produce exactly that.
const (
	CapContainerRuntime = "container-runtime"
	CapPackageManager   = "package-manager"
	CapServiceManager   = "service-manager"
	CapFirewall         = "firewall"
	CapOverlay          = "overlay"
	CapGraphicalSession = "graphical-session"
	// CapSeat is hardware: somewhere a display server COULD run. CapGraphicalSession above is
	// state: whether one IS running. Assignment needs the first.
	CapSeat       = "seat"
	CapPrivileged = "privileged"

	// The network manager this machine runs, one capability per dialect (novox/hq ADR 0161): the
	// uplink seat's holder declares its own, so the holder for a manager the machine does not run
	// is refused the way any missing capability is, naming it. Active, not installed — a machine
	// may have two of these on disk and runs one.
	CapUplinkNetworkManager  = "uplink-networkmanager"
	CapUplinkSystemdNetworkd = "uplink-systemd-networkd"
	CapUplinkDhcpcd          = "uplink-dhcpcd"
)

// commandCapability is the shape most detectors take: run something, and treat a working
// invocation as evidence.
//
// It runs a command that only succeeds if the thing is FUNCTIONING, never `--version` alone.
// A version string proves a binary is on disk, which is the assumption 04-ISSUES/007 records
// as false: the package was installed and the daemon was not running.
type commandCapability struct {
	name    string
	command string
	args    []string
	// why describes what a success actually proves, and is reported as the detector's `How`.
	why string
	// interpret decides the verdict from what the command said and how it exited.
	//
	// Exists because "exit zero" is not a universal answer. A degraded service manager reports
	// its state on stdout and exits non-zero — it is running, and reading only the exit code
	// declared no service manager on a machine whose init it was. That is 04-ISSUES/007 in the
	// mirror: 007 is installed-but-broken reported present; this is working-but-imperfect
	// reported absent. Both place work wrongly, and this one was only visible by running
	// against a real machine.
	//
	// nil means the ordinary rule: success is exit zero.
	interpret func(stdout string, err error) (present bool, detail string)
	runner    Runner
}

func (c commandCapability) Name() string { return c.name }

func (c commandCapability) Detect(ctx context.Context) Verdict {
	out, err := c.runner(ctx, c.command, c.args...)

	interpret := c.interpret
	if interpret == nil {
		interpret = exitZero
	}
	present, detail := interpret(out, err)

	if strings.TrimSpace(detail) == "" {
		// A verdict with no reason is the fault in a new place: something nobody can act on.
		// Reached when a command fails silently, which systemctl does.
		if present {
			detail = "responded"
		} else {
			detail = fmt.Sprintf("%s gave no reason", c.command)
		}
	}
	return Verdict{Name: c.name, Present: present, Detail: firstLine(detail), How: c.why}
}

// exitZero is the ordinary rule: the command worked, so the capability is there.
func exitZero(stdout string, err error) (bool, string) {
	if err != nil {
		return false, err.Error()
	}
	return true, stdout
}

// systemRunning reads what an init system says about itself rather than how it exited.
//
// `is-system-running` exits non-zero for every state except `running` — including `degraded`,
// which means units failed and the init is emphatically present. Treating that as absent made
// a machine running systemd report no service manager.
func systemRunning(stdout string, err error) (bool, string) {
	state := strings.TrimSpace(firstLine(stdout))
	switch state {
	case "running", "degraded", "starting", "maintenance", "stopping":
		return true, state
	case "":
		if err != nil {
			return false, err.Error()
		}
		return false, "said nothing"
	default:
		// `offline` and `unknown` mean it is not managing this machine.
		return false, state
	}
}

func firstLine(s string) string {
	s = strings.TrimSpace(s)
	if i := strings.IndexByte(s, '\n'); i >= 0 {
		s = s[:i]
	}
	if len(s) > 200 {
		s = s[:200] + "…"
	}
	return s
}

// privileged reports whether the host can change this machine at all.
//
// Reported as a capability rather than checked at startup on purpose: a host that cannot act
// is still a host that can report, and novox/hq ADR 0004 says what varies between nodes lives
// here rather than in the definition of a node.
type privileged struct{}

func (privileged) Name() string { return CapPrivileged }

func (privileged) Detect(context.Context) Verdict {
	uid := os.Geteuid()
	if uid == 0 {
		return Verdict{
			Name: CapPrivileged, Present: true,
			Detail: "effective uid 0",
			How:    "effective uid — the host changes a machine, which needs root",
		}
	}
	return Verdict{
		Name: CapPrivileged, Present: false,
		Detail: fmt.Sprintf("effective uid %d, not 0", uid),
		How:    "effective uid — the host changes a machine, which needs root",
	}
}

// graphicalSession reports whether anything could display a window here.
//
// Environment rather than a probe, because a display server is reachable through a socket a
// detector would have to guess at, and the variables are what an application would use anyway.
// Stated so the limit is visible: this detects that a session is ADVERTISED, which is weaker
// than the other detectors here.
type graphicalSession struct{}

func (graphicalSession) Name() string { return CapGraphicalSession }

func (graphicalSession) Detect(context.Context) Verdict {
	const how = "DISPLAY / WAYLAND_DISPLAY — weaker than the other checks: advertised, not probed"
	if d := os.Getenv("WAYLAND_DISPLAY"); d != "" {
		return Verdict{Name: CapGraphicalSession, Present: true, Detail: "wayland: " + d, How: how}
	}
	if d := os.Getenv("DISPLAY"); d != "" {
		return Verdict{Name: CapGraphicalSession, Present: true, Detail: "x11: " + d, How: how}
	}
	return Verdict{
		Name: CapGraphicalSession, Present: false,
		Detail: "neither DISPLAY nor WAYLAND_DISPLAY is set",
		How:    how,
	}
}

// Default returns the detectors the host runs when nobody says otherwise.
//
// Each command is chosen to prove the thing WORKS rather than exists:
//   - the container runtime is asked for server-side information, which fails when the daemon
//     is down even though the client is installed — the exact shape of 04-ISSUES/007;
//   - the service manager is asked whether it is the running init, not whether it is present;
//   - the firewall is asked to list a ruleset, which needs both the tool and the permission.
func Default(runner Runner) []Detector {
	if runner == nil {
		runner = ExecRunner
	}
	return []Detector{
		privileged{},
		graphicalSession{},
		seat{},
		commandCapability{
			name: CapContainerRuntime, command: "docker", args: []string{"info", "--format", "{{.ServerVersion}}"},
			why:    "asks the daemon for its version — a running daemon, not an installed client",
			runner: runner,
		},
		commandCapability{
			name: CapPackageManager, command: "pacman", args: []string{"-Q", "pacman"},
			why:    "queries the package database — a working database, not a binary on disk",
			runner: runner,
		},
		commandCapability{
			name: CapServiceManager, command: "systemctl", args: []string{"is-system-running"},
			why:       "reads the init's own account of its state — degraded is still running",
			interpret: systemRunning,
			runner:    runner,
		},
		commandCapability{
			name: CapFirewall, command: "nft", args: []string{"list", "ruleset"},
			why:    "lists the ruleset — needs the tool AND the privilege to use it",
			runner: runner,
		},
		commandCapability{
			name: CapOverlay, command: "wg", args: []string{"show", "interfaces"},
			why:    "asks the kernel for interfaces — needs the module, not just the tool",
			runner: runner,
		},
		commandCapability{
			name: CapUplinkNetworkManager, command: "systemctl", args: []string{"is-active", "NetworkManager.service"},
			why:    "asks the init whether NetworkManager is running — the dialect the uplink seat's holder must speak",
			runner: runner,
		},
		commandCapability{
			name: CapUplinkSystemdNetworkd, command: "systemctl", args: []string{"is-active", "systemd-networkd.service"},
			why:    "asks the init whether systemd-networkd is running — the dialect the uplink seat's holder must speak",
			runner: runner,
		},
		commandCapability{
			name: CapUplinkDhcpcd, command: "systemctl", args: []string{"is-active", "dhcpcd.service"},
			why:    "asks the init whether dhcpcd is running — the dialect the uplink seat's holder must speak",
			runner: runner,
		},
	}
}

// isRoot is the same question `privileged` answers, exposed for tests that must check the
// detector against something other than itself.
func isRoot() bool { return os.Geteuid() == 0 }