echolot/server/internal/config/config.go

// SPDX-FileCopyrightText: 2026 Echolot contributors
// SPDX-License-Identifier: GPL-3.0-or-later

// Package config resolves server configuration with the precedence
// flags > environment > defaults. In Docker mode (detected or forced with
// --docker) env vars are the expected source; native installs typically use
// flags baked into the systemd unit by --install-systemd.
package config

import (
	"flag"
	"fmt"
	"io"
	"net"
	"os"
	"strconv"
	"strings"
)

// Config holds everything the daemon needs. Every field maps to exactly one
// env var (ECHOLOT_*) and one flag; keep the three in sync when adding fields.
type Config struct {
	// Control plane (HTTPS + JSON). TLS is pin-based per spec §1: self-signed
	// is first-class, so cert+key are generated if the paths don't exist.
	ControlListen string // ECHOLOT_CONTROL_LISTEN / --control-listen
	TLSCert       string // ECHOLOT_TLS_CERT / --tls-cert
	TLSKey        string // ECHOLOT_TLS_KEY / --tls-key

	// Data plane
	UDPListen  string // ECHOLOT_UDP_LISTEN / --udp-listen (spec default port 8442)
	TCPListen  string // ECHOLOT_TCP_LISTEN / --tcp-listen (spec default port 8441)
	StunListen string // ECHOLOT_STUN_LISTEN / --stun-listen (spec default 3478; empty disables)
	DNSListen  string // ECHOLOT_DNS_LISTEN / --dns-listen (canary zone; empty disables)
	CanaryZone string // ECHOLOT_CANARY_ZONE / --canary-zone (e.g. c.echo-lot.app)
	// Optional cleartext HTTP-echo listener (spec §4 plaintext-path test).
	// Default empty = off; it exposes only POST /v1/echo, no auth, no secrets.
	HTTPEchoListen string // ECHOLOT_HTTP_ECHO_LISTEN / --http-echo-listen
	// Comma-separated anchors for the egress-MTU self-proof (host or ip).
	MTUProbeTargets string // ECHOLOT_MTU_PROBE_TARGETS / --mtu-probe-targets

	// Admin UI / health listener (spec §7: localhost-only by default)
	AdminListen string // ECHOLOT_ADMIN_LISTEN / --admin-listen

	// ReservedAddrs are IPs reserved for measurement: addresses whose listening state must stay
	// known, so that "nothing answered on port 443" is a fact about the network rather than a
	// fact about this server's configuration. Enforced by CheckReserved.
	ReservedAddrs string // ECHOLOT_RESERVED_ADDRS / --reserved-addrs

	// State directory: device store, generated TLS material.
	StateDir string // ECHOLOT_STATE_DIR / --state-dir

	// Profile identity
	Name string // ECHOLOT_NAME / --name (profile "name", e.g. "homelab")

	// Self-update (native mode only; ignored in containers — images update
	// by pulling a new tag). Empty = disabled. Value: Gitea repo API base,
	// e.g. https://git.example.net/api/v1/repos/owner/repo
	SelfUpdateAPI string // ECHOLOT_SELF_UPDATE_API / --self-update-api

	// Uploaded-run storage. The default is "anonymous": any enrolled device may upload,
	// which is what a self-hosted server wants. Operators of shared servers turn it down.
	UploadsMode         string // ECHOLOT_UPLOADS / --uploads (off|anonymous|account)
	UploadMaxBytes      int64  // ECHOLOT_UPLOAD_MAX_BYTES / --upload-max-bytes
	UploadRetentionDays int    // ECHOLOT_UPLOAD_RETENTION_DAYS / --upload-retention-days
	UploadMaxRuns       int    // ECHOLOT_UPLOAD_MAX_RUNS / --upload-max-runs (per device)
	UploadMinAnon       string // ECHOLOT_UPLOAD_MIN_ANONYMIZATION / --upload-min-anonymization

	// Client compatibility window. Bounds are SemVer; an empty maximum means unbounded. The
	// defaults sit at breaking boundaries, so shipping a patch never requires changing them.
	MinAppVersion string // ECHOLOT_MIN_APP_VERSION / --min-app-version
	MaxAppVersion string // ECHOLOT_MAX_APP_VERSION / --max-app-version (exclusive)

	// Where clients reach the control plane, for enrollment links. Empty = derive from the
	// first control listen address.
	PublicControlURL string // ECHOLOT_PUBLIC_URL / --public-url

	// Identity provider. Empty issuer disables sign-in entirely; the server is a relying
	// party and never stores passwords.
	OIDCIssuer      string // ECHOLOT_OIDC_ISSUER / --oidc-issuer
	OIDCClientID    string // ECHOLOT_OIDC_CLIENT_ID / --oidc-client-id (confidential, admin UI)
	OIDCAppClientID string // ECHOLOT_OIDC_APP_CLIENT_ID / --oidc-app-client-id (public, the phone app)
	// Issuer for the app's client, when the IdP gives each application its own.
	//
	// Authentik derives the issuer from the application slug, so two applications mean two
	// issuers — and a token's `iss` must match the one that minted it. Empty means both clients
	// share ECHOLOT_OIDC_ISSUER, which is what IdPs with a single global issuer do.
	OIDCAppIssuer  string // ECHOLOT_OIDC_APP_ISSUER / --oidc-app-issuer
	OIDCAdminGroup string // ECHOLOT_OIDC_ADMIN_GROUP / --oidc-admin-group

	// Break-glass admin username; the password lives hashed in the state store.
	AdminUser string // ECHOLOT_ADMIN_USER / --admin-user

	// Secret for the *confidential* admin client. Prefer ECHOLOT_OIDC_CLIENT_SECRET_FILE: a path
	// keeps the secret out of the environment, where it is readable by anything that can see
	// /proc/<pid>/environ and lands in every dump of the unit's configuration.
	OIDCClientSecret string // ECHOLOT_OIDC_CLIENT_SECRET / _FILE

	// Where the admin UI is reachable, used to build the OIDC redirect URI. Must match what is
	// registered at the IdP exactly.
	AdminBaseURL string // ECHOLOT_ADMIN_BASE_URL / --admin-base-url
	// TLS for the admin listener. Without these it serves plaintext, which is only acceptable on
	// loopback — see checkAdminExposure.
	AdminTLSCert string // ECHOLOT_ADMIN_TLS_CERT / --admin-tls-cert
	AdminTLSKey  string // ECHOLOT_ADMIN_TLS_KEY / --admin-tls-key
	// Deliberate override for serving the admin UI in plaintext off loopback, so that decision
	// is made rather than stumbled into.
	AdminInsecure bool // ECHOLOT_ADMIN_INSECURE / --admin-insecure

	// Port-80 listener that answers ACME HTTP-01 challenges and redirects everything else to
	// the admin UI. Empty disables it. HTTP-01 always arrives on port 80 — the CA picks the
	// port — so this never collides with the admin UI on 443.
	ACMEHTTPListen string // ECHOLOT_ACME_HTTP_LISTEN / --acme-http-listen
	// Directory an ACME client writes challenge tokens into. Defaults to <state-dir>/acme.
	ACMEWebroot string // ECHOLOT_ACME_WEBROOT / --acme-webroot

	// Mode
	Docker bool // --docker (or autodetected; env ECHOLOT_DOCKER=1 forces)
}

// secretOr reads ECHOLOT_<key>, or the contents of the file named by ECHOLOT_<key>_FILE.
//
// The file form exists because a secret in the environment is readable by anything that can see
// /proc/<pid>/environ and lands in every dump of the unit's configuration. A path costs nothing
// and keeps the value in one file whose permissions an operator can reason about.
func secretOr(key, def string) string {
	if path := envOr(key+"_FILE", ""); path != "" {
		if b, err := os.ReadFile(path); err == nil {
			return strings.TrimSpace(string(b))
		}
	}
	return envOr(key, def)
}

// envInt reads ECHOLOT_<key> as an integer with a fallback.
func envInt(key string, def int) int {
	if v := envOr(key, ""); v != "" {
		if n, err := strconv.Atoi(v); err == nil {
			return n
		}
	}
	return def
}

// envOr reads ECHOLOT_<key> with a fallback.
func envOr(key, def string) string {
	if v, ok := os.LookupEnv("ECHOLOT_" + key); ok {
		return v
	}
	return def
}

// Load parses flags/env. Returns the config plus the action flags that make
// the process do something other than serve (install/uninstall/update).
func Load(args []string) (*Config, *Actions, error) {
	fs := flag.NewFlagSet("echolot-server", flag.ContinueOnError)
	c := &Config{}
	a := &Actions{}

	fs.StringVar(&c.ControlListen, "control-listen", envOr("CONTROL_LISTEN", ":8443"), "control-plane HTTPS listen address(es), comma-separated")
	fs.StringVar(&c.TLSCert, "tls-cert", envOr("TLS_CERT", ""), "TLS cert path (empty: self-signed in state dir)")
	fs.StringVar(&c.TLSKey, "tls-key", envOr("TLS_KEY", ""), "TLS key path (empty: self-signed in state dir)")
	fs.StringVar(&c.UDPListen, "udp-listen", envOr("UDP_LISTEN", ":8442"), "UDP data-plane listen address(es), comma-separated")
	fs.StringVar(&c.TCPListen, "tcp-listen", envOr("TCP_LISTEN", ":8441"), "TCP echo listen address(es), comma-separated")
	fs.StringVar(&c.StunListen, "stun-listen", envOr("STUN_LISTEN", ":3478"), "STUN listen address(es), comma-separated; empty disables (spec §4)")
	fs.StringVar(&c.DNSListen, "dns-listen", envOr("DNS_LISTEN", ""), "canary-DNS listen address(es) udp+tcp/53, comma-separated; empty disables (spec §6.1)")
	fs.StringVar(&c.CanaryZone, "canary-zone", envOr("CANARY_ZONE", ""), "authoritative canary zone, e.g. c.echo-lot.app")
	fs.StringVar(&c.HTTPEchoListen, "http-echo-listen", envOr("HTTP_ECHO_LISTEN", ""), "optional CLEARTEXT http-echo listen address(es); empty disables (spec §4)")
	fs.StringVar(&c.MTUProbeTargets, "mtu-probe-targets", envOr("MTU_PROBE_TARGETS", "1.1.1.1,2606:4700:4700::1111"), "egress-MTU self-proof anchors, comma-separated")
	fs.StringVar(&c.AdminListen, "admin-listen", envOr("ADMIN_LISTEN", "127.0.0.1:8444"), "admin/health listen address (keep localhost)")
	fs.StringVar(&c.ReservedAddrs, "reserved-addrs", envOr("RESERVED_ADDRS", ""), "comma-separated IPs reserved for measurement; no listener but the STUN alternate may bind them")
	fs.StringVar(&c.StateDir, "state-dir", envOr("STATE_DIR", defaultStateDir()), "state directory (device store, generated TLS)")
	fs.StringVar(&c.Name, "name", envOr("NAME", "echolot"), "server profile name")
	fs.StringVar(&c.SelfUpdateAPI, "self-update-api", envOr("SELF_UPDATE_API", ""), "Gitea repo API base for self-update; empty disables")
	fs.StringVar(&c.UploadsMode, "uploads", envOr("UPLOADS", "anonymous"), "who may upload measurement runs: off|anonymous|account")
	fs.Int64Var(&c.UploadMaxBytes, "upload-max-bytes", int64(envInt("UPLOAD_MAX_BYTES", 4<<20)), "largest accepted uploaded run, bytes")
	fs.IntVar(&c.UploadRetentionDays, "upload-retention-days", envInt("UPLOAD_RETENTION_DAYS", 90), "delete uploaded runs older than this; 0 disables")
	fs.IntVar(&c.UploadMaxRuns, "upload-max-runs", envInt("UPLOAD_MAX_RUNS", 200), "keep at most this many runs per device; 0 disables")
	fs.StringVar(&c.UploadMinAnon, "upload-min-anonymization", envOr("UPLOAD_MIN_ANONYMIZATION", "full"), "least anonymization accepted: full|balanced|strict")
	fs.StringVar(&c.OIDCIssuer, "oidc-issuer", envOr("OIDC_ISSUER", ""), "OpenID Connect issuer URL; empty disables sign-in")
	fs.StringVar(&c.OIDCClientID, "oidc-client-id", envOr("OIDC_CLIENT_ID", ""), "confidential OIDC client id for the admin UI")
	fs.StringVar(&c.OIDCAppClientID, "oidc-app-client-id", envOr("OIDC_APP_CLIENT_ID", ""), "public OIDC client id used by the Android app (PKCE)")
	fs.StringVar(&c.OIDCAppIssuer, "oidc-app-issuer", envOr("OIDC_APP_ISSUER", ""), "issuer for the app client when the IdP uses per-application issuers; empty = same as --oidc-issuer")
	fs.StringVar(&c.OIDCAdminGroup, "oidc-admin-group", envOr("OIDC_ADMIN_GROUP", ""), "group claim required for admin access; empty means nobody is an admin via OIDC")
	fs.StringVar(&c.OIDCClientSecret, "oidc-client-secret", secretOr("OIDC_CLIENT_SECRET", ""), "secret for the confidential admin client; prefer ECHOLOT_OIDC_CLIENT_SECRET_FILE")
	fs.StringVar(&c.AdminBaseURL, "admin-base-url", envOr("ADMIN_BASE_URL", ""), "public URL of the admin UI, for the OIDC redirect (e.g. https://admin.example.net)")
	fs.StringVar(&c.AdminTLSCert, "admin-tls-cert", envOr("ADMIN_TLS_CERT", ""), "TLS certificate for the admin listener")
	fs.StringVar(&c.AdminTLSKey, "admin-tls-key", envOr("ADMIN_TLS_KEY", ""), "TLS key for the admin listener")
	fs.BoolVar(&c.AdminInsecure, "admin-insecure", envOr("ADMIN_INSECURE", "") == "1", "allow the admin UI in plaintext off loopback (you are on your own)")
	fs.StringVar(&c.ACMEHTTPListen, "acme-http-listen", envOr("ACME_HTTP_LISTEN", ""), "port-80 listener for ACME HTTP-01 challenges and http->https redirects")
	fs.StringVar(&c.ACMEWebroot, "acme-webroot", envOr("ACME_WEBROOT", ""), "directory an ACME client writes challenges into (default <state-dir>/acme)")
	fs.StringVar(&c.PublicControlURL, "public-url", envOr("PUBLIC_URL", ""), "public control-plane URL for enrollment links, e.g. https://probe.example.net:8443")
	fs.StringVar(&c.MinAppVersion, "min-app-version", envOr("MIN_APP_VERSION", "0.2.0"), "oldest app version this server will serve (SemVer, inclusive)")
	fs.StringVar(&c.MaxAppVersion, "max-app-version", envOr("MAX_APP_VERSION", "1.0.0"), "first app version this server will refuse (SemVer, exclusive); empty = unbounded")
	fs.BoolVar(&c.Docker, "docker", envOr("DOCKER", "") == "1", "force container mode (config from env, no systemd/self-update)")

	fs.BoolVar(&a.InstallSystemd, "install-systemd", false, "install a systemd unit for this binary and exit")
	fs.BoolVar(&a.UninstallSystemd, "uninstall-systemd", false, "remove the systemd unit and exit")
	var daemon bool
	fs.BoolVar(&a.Serve, "serve", false, "run the server (bind listeners and answer requests)")
	fs.BoolVar(&daemon, "daemon", false, "alias for --serve")
	fs.BoolVar(&a.SetAdminPassword, "set-admin-password", false,
		"set the break-glass admin password (username as --admin-user, password read from stdin) and exit")
	fs.StringVar(&c.AdminUser, "admin-user", envOr("ADMIN_USER", "admin"), "username for the break-glass admin")
	fs.BoolVar(&a.SelfUpdate, "self-update", false, "check for a newer release, replace this binary, and exit")
	fs.BoolVar(&a.Version, "version", false, "print version and exit")

	if err := fs.Parse(args); err != nil {
		return nil, nil, err
	}
	if !c.Docker {
		c.Docker = inContainer()
	}
	a.Serve = a.Serve || daemon
	// No verb at all means the caller has not said what they want. Usage is the answer, and it
	// is a usage error rather than success — otherwise a service manager sees a clean exit and
	// concludes the server ran and finished.
	if !a.Serve && !a.InstallSystemd && !a.UninstallSystemd && !a.SelfUpdate &&
		!a.SetAdminPassword && !a.Version {
		a.Help = true
	}
	if a.Serve {
		if err := c.checkAdminExposure(); err != nil {
			return nil, nil, err
		}
		if err := c.CheckReserved(c.Listeners()); err != nil {
			return nil, nil, err
		}
	}
	if c.Docker && (a.InstallSystemd || a.UninstallSystemd || a.SelfUpdate) {
		return nil, nil, fmt.Errorf("systemd/self-update actions are native-mode only (container detected; override with ECHOLOT_DOCKER=0 if this is wrong)")
	}
	return c, a, nil
}

// Usage prints the verbs first and the tuning flags second, because the question someone has
// when they run this by name is "what does it do", not "what can I set".
func Usage(w io.Writer) {
	fmt.Fprint(w, `echolot-server — the Echolot probe server

USAGE
  echolot-server --serve                 run the server
  echolot-server --version               print the version
  echolot-server --install-systemd       install and enable a systemd unit
  echolot-server --uninstall-systemd     remove it
  echolot-server --self-update           replace this binary with the latest release
  echolot-server --set-admin-password    set the break-glass admin password (stdin)
  echolot-server --help                  full flag list

Every flag can also be set as an environment variable: --control-listen becomes
ECHOLOT_CONTROL_LISTEN. In a container, configuration comes from the environment.

Running with no verb prints this and exits non-zero: starting to serve the internet
should be something you asked for.
`)
}

// checkAdminExposure refuses to serve an unencrypted admin UI on a non-loopback address.
//
// The admin session cookie is a bearer credential for everything this server can do, and the OIDC
// authorization code arrives in a URL. In plaintext, both are readable by anyone on the path — and
// on a globally routable address "the path" means the internet. This is a hard stop rather than a
// warning because a warning in a log is not read by the person who most needs it, and because the
// two safe answers are cheap: bind to loopback and tunnel, or supply a certificate.
func (c *Config) checkAdminExposure() error {
	if c.AdminTLSCert != "" || c.AdminInsecure {
		return nil
	}
	for _, addr := range Addrs(c.AdminListen) {
		host, _, err := net.SplitHostPort(addr)
		if err != nil {
			continue
		}
		ip := net.ParseIP(strings.Trim(host, "[]"))
		if host == "" || ip == nil || ip.IsLoopback() {
			continue // loopback, or a name we cannot judge; RFC 8252 blesses loopback plaintext
		}
		return fmt.Errorf(
			"refusing to serve the admin UI in plaintext on %s: the session cookie and the OIDC "+
				"authorization code would cross the network in the clear.\n"+
				"  Fix it one of three ways:\n"+
				"    - bind to 127.0.0.1 and reach it over an SSH tunnel (no certificate needed)\n"+
				"    - set ECHOLOT_ADMIN_TLS_CERT and ECHOLOT_ADMIN_TLS_KEY\n"+
				"    - set ECHOLOT_ADMIN_INSECURE=1 if you genuinely mean it", addr)
	}
	return nil
}

// Listeners enumerates every configured listen spec, for CheckReserved.
//
// Kept as one list here rather than checked at each call site, so a listener added later is
// caught by the compiler when this function is updated — and, more to the point, so that the
// person adding one sees the reserved-address rule exists at all.
func (c *Config) Listeners() []Listener {
	return []Listener{
		// The instrument: these belong on the reserved addresses as much as anywhere.
		{Name: "control-listen", Spec: c.ControlListen, Measurement: true},
		{Name: "udp-listen", Spec: c.UDPListen, Measurement: true},
		{Name: "tcp-listen", Spec: c.TCPListen, Measurement: true},
		{Name: "dns-listen", Spec: c.DNSListen, Measurement: true},
		{Name: "stun-listen", Spec: c.StunListen, Measurement: true},
		// http-echo is deliberately not marked as measurement: it is cleartext HTTP, so on a
		// reserved address it would be the very listener that ruins the port-80 test.
		{Name: "http-echo-listen", Spec: c.HTTPEchoListen},
		// Services. These have no business on an address kept for measuring.
		{Name: "admin-listen", Spec: c.AdminListen},
		{Name: "acme-http-listen", Spec: c.ACMEHTTPListen},
	}
}

// Addrs splits a comma-separated listen spec into individual addresses.
// Explicit per-address binds matter on multi-IP hosts: a wildcard bind
// (":8443") would also claim addresses reserved for other purposes (e.g. an
// SSH-only management IP).
func Addrs(spec string) []string {
	var out []string
	for _, a := range strings.Split(spec, ",") {
		if a = strings.TrimSpace(a); a != "" {
			out = append(out, a)
		}
	}
	return out
}

// Actions are the verbs. Serving is one of them, and it is explicit: running the binary with no
// arguments prints usage rather than binding a dozen ports and starting to answer the internet.
// Someone typing the name of an unfamiliar program on a terminal should be told what it does, not
// have it start doing it.
type Actions struct {
	Serve bool
	// Help is set when there is nothing to do: no verb was given.
	Help bool

	InstallSystemd   bool
	UninstallSystemd bool
	SelfUpdate       bool
	SetAdminPassword bool
	Version          bool
}

func defaultStateDir() string {
	if os.Geteuid() == 0 {
		return "/var/lib/echolot-server"
	}
	home, err := os.UserHomeDir()
	if err != nil {
		return "./echolot-state"
	}
	return home + "/.local/share/echolot-server"
}

// inContainer detects Docker/Podman/K8s without being asked: /.dockerenv,
// /run/.containerenv (podman), or a container hint in /proc/1/cgroup
// (cgroup v1 era) / KUBERNETES_SERVICE_HOST. Best-effort — --docker and
// ECHOLOT_DOCKER always win.
func inContainer() bool {
	for _, marker := range []string{"/.dockerenv", "/run/.containerenv"} {
		if _, err := os.Stat(marker); err == nil {
			return true
		}
	}
	if os.Getenv("KUBERNETES_SERVICE_HOST") != "" {
		return true
	}
	if b, err := os.ReadFile("/proc/1/cgroup"); err == nil {
		s := string(b)
		if strings.Contains(s, "docker") || strings.Contains(s, "containerd") || strings.Contains(s, "kubepods") {
			return true
		}
	}
	return false
}