ZDDC/zddc/internal/config/config.go

package config

import (
	"errors"
	"flag"
	"fmt"
	"io"
	"net"
	"os"
	"path/filepath"
	"strings"
	"time"
)

// Config holds all runtime configuration. Each field can be set via a
// command-line flag (--<name>) or environment variable (ZDDC_<NAME>);
// the flag takes precedence when both are present.
type Config struct {
	Root        string   // --root / ZDDC_ROOT — served file tree (default: CWD)
	Addr        string   // --addr / ZDDC_ADDR — bind address (default :8443)
	TLSCert     string   // --tls-cert / ZDDC_TLS_CERT — PEM cert path; "none" = plain HTTP; empty = self-signed
	TLSKey      string   // --tls-key / ZDDC_TLS_KEY — PEM key path
	TLSMode     string   // computed: none/selfsigned/provided
	LogLevel    string   // --log-level / ZDDC_LOG_LEVEL — debug/info/warn/error (default info)
	IndexPath   string   // --index-path / ZDDC_INDEX_PATH — virtual archive prefix (default .archive)
	EmailHeader string   // --email-header / ZDDC_EMAIL_HEADER — auth header name (default X-Auth-Request-Email)
	CORSOrigins []string // --cors-origin / ZDDC_CORS_ORIGIN — comma-separated allowlist; default empty (CORS disabled); explicit value enables
	AccessLog   string   // --access-log / ZDDC_ACCESS_LOG — file path for tee'd JSON access log; empty = stderr only
	Insecure    bool     // --insecure / ZDDC_INSECURE=1 — opt out of safety checks (currently: allow start without a root .zddc, leaving the tree publicly accessible)
	NoAuth      bool     // --no-auth / ZDDC_NO_AUTH=1 — skip ACL enforcement entirely. This instance is NOT the security boundary; on master = "open" (anyone reads everything), on a client = "trust upstream's filtering, don't re-evaluate ACLs locally."

	// Client-mode flags. When Upstream is non-empty, this binary runs
	// as a downstream proxy/cache/mirror against the named master.
	// Root then becomes the cache directory rather than the served
	// data root. Master-mode flags (apps, archive, opa, etc.) are
	// ignored in client mode — see cmd/zddc-server/main.go.
	Upstream       string        // --upstream / ZDDC_UPSTREAM — master URL (https://master.example.com); empty = run as master
	Mode           string        // --mode / ZDDC_MODE — "proxy" (no disk persistence), "cache" (default; persist on access), "mirror" (cache + access-triggered subtree warmer)
	BearerFile     string        // --bearer-file / ZDDC_BEARER_FILE — path to a 0600 file containing the master-issued token to forward upstream
	SkipTLSVerify  bool          // --skip-tls-verify / ZDDC_SKIP_TLS_VERIFY=1 — accept self-signed / untrusted upstream certs. Distinct from --no-auth; intended for dev/internal CA scenarios only.
	MirrorSubtree     []string      // --mirror-subtree / ZDDC_MIRROR_SUBTREE — comma-separated subtree URL paths the access-triggered walker keeps current. Default `/` when --mode=mirror and unset; ignored otherwise.
	MirrorMinInterval time.Duration // --mirror-min-interval / ZDDC_MIRROR_MIN_INTERVAL — minimum gap between walks of the same subtree. Idle subtrees stay quiet; bumping this reduces upstream load on busy mirrors. Default 1h.
	OPAURL       string        // --opa-url / ZDDC_OPA_URL — policy decider endpoint: "internal" (default), "http(s)://..." (real OPA via HTTP), or "unix:///..." (OPA via Unix socket)
	OPAFailOpen  bool          // --opa-fail-open / ZDDC_OPA_FAIL_OPEN=1 — when external OPA is unreachable, allow instead of deny (default: fail closed)
	OPACacheTTL  time.Duration // --opa-cache-ttl / ZDDC_OPA_CACHE_TTL — external mode only: per-decision cache TTL. Default 1s. Set 0s to disable.
	AppsPubKey   string        // --apps-pubkey / ZDDC_APPS_PUBKEY — path to the Ed25519 public key (PEM) used to verify Ed25519 signatures on URL-fetched apps: artifacts. Empty = URL apps disabled (only embedded + local-path apps work). Operators using zddc.varasys.io's canonical channels download pubkey.pem from there.
	MaxWriteBytes int64        // --max-write-bytes / ZDDC_MAX_WRITE_BYTES — upper bound on PUT body size. Default 256 MiB. Per-request limit; rejected with 413.
	ArchiveRescanInterval time.Duration // --archive-rescan-interval / ZDDC_ARCHIVE_RESCAN_INTERVAL — periodic full re-walk of the archive index. Covers SMB/CIFS where inotify misses cross-client writes. Default 60s; 0 to disable.

	// MD→{docx,html,pdf} conversion endpoint (see internal/convert).
	// The server shells out to upstream pandoc + chromium container
	// images via podman or docker, pulling each on first use via
	// `--pull=missing`. No custom image build is required — only that
	// podman or docker is on PATH and the configured image refs are
	// reachable. If no runtime is found the endpoint serves 503.
	ConvertPandocImage   string        // --convert-pandoc-image / ZDDC_CONVERT_PANDOC_IMAGE — image for MD→DOCX/HTML. Default docker.io/pandoc/latex:latest.
	ConvertChromiumImage string        // --convert-chromium-image / ZDDC_CONVERT_CHROMIUM_IMAGE — image for HTML→PDF. Default docker.io/zenika/alpine-chrome:latest.
	ConvertEngine        string        // --convert-engine / ZDDC_CONVERT_ENGINE — override engine binary (default: probe for podman, then docker).
	ConvertPodmanSocket  string        // --convert-podman-socket / ZDDC_CONVERT_PODMAN_SOCKET — when non-empty, run podman in remote mode against this Unix socket (e.g. unix:///var/run/podman/podman.sock). Used with the Kubernetes sidecar pattern so zddc-server's own pod stays unprivileged.
	ConvertScratchDir    string        // --convert-scratch-dir / ZDDC_CONVERT_SCRATCH_DIR — directory used for per-conversion scratch (template + HTML/PDF intermediates). Must be a path the remote podman can see at the same path. Empty = use $TMPDIR (local-mode default).
	ConvertMemMiB        int           // --convert-mem-mib / ZDDC_CONVERT_MEM_MIB — per-container memory cap in MiB. Default 512.
	ConvertCPUs          string        // --convert-cpus / ZDDC_CONVERT_CPUS — per-container CPU limit. Default "2".
	ConvertPIDs          int           // --convert-pids / ZDDC_CONVERT_PIDS — per-container PID limit. Default 100.
	ConvertTimeout       time.Duration // --convert-timeout / ZDDC_CONVERT_TIMEOUT — per-conversion wall clock. Default 30s.
}

// ErrHelpRequested is returned by Load when --help is passed; the caller
// should print Usage() to stderr and exit 0.
var ErrHelpRequested = errors.New("help requested")

// ErrVersionRequested is returned by Load when --version is passed; the
// caller should print version info and exit 0.
var ErrVersionRequested = errors.New("version requested")

// Load reads configuration from CLI flags + environment variables.
//
// Precedence (highest → lowest): command-line flag, environment variable,
// hard-coded default. Special-cases:
//   - --root / ZDDC_ROOT default to the current working directory if both
//     are unset, so an operator can `cd /srv/zddc && zddc-server` with
//     zero config.
//   - --version and --help return distinguished sentinel errors; the caller
//     handles printing and exit. Pass nil for args to skip flag parsing
//     entirely (used by tests that set state via env vars only).
//
// Standard usage from main.go:
//
//	cfg, err := config.Load(os.Args[1:])
//	if errors.Is(err, config.ErrHelpRequested) { os.Exit(0) }
//	if errors.Is(err, config.ErrVersionRequested) { /* print versions */ ; os.Exit(0) }
//	if err != nil { ... }
func Load(args []string) (Config, error) {
	fs := flag.NewFlagSet("zddc-server", flag.ContinueOnError)
	// Discard flag's own error output; we wrap and return our own.
	fs.SetOutput(io.Discard)

	rootFlag := fs.String("root", os.Getenv("ZDDC_ROOT"),
		"Path to the served file tree. Default: ZDDC_ROOT or the current directory.")
	addrFlag := fs.String("addr", getEnv("ZDDC_ADDR", ":8443"),
		"Listen address (host:port). Default: ZDDC_ADDR or :8443. **In client mode (--upstream set) the default downgrades to 127.0.0.1:8443** unless --addr/ZDDC_ADDR is set explicitly — the cache layer forwards a bearer to upstream without authenticating the local caller, so a non-loopback bind needs --insecure-direct to acknowledge an authenticating reverse proxy / network policy is in front.")
	tlsCertFlag := fs.String("tls-cert", os.Getenv("ZDDC_TLS_CERT"),
		"Path to a PEM TLS certificate. \"none\" disables TLS (plain HTTP). Empty means self-signed.")
	tlsKeyFlag := fs.String("tls-key", os.Getenv("ZDDC_TLS_KEY"),
		"Path to the matching PEM TLS private key.")
	logLevelFlag := fs.String("log-level", getEnv("ZDDC_LOG_LEVEL", "info"),
		"Log level: debug, info, warn, error.")
	indexPathFlag := fs.String("index-path", getEnv("ZDDC_INDEX_PATH", ".archive"),
		"URL segment that triggers the virtual archive index (default \".archive\").")
	emailHeaderFlag := fs.String("email-header", getEnv("ZDDC_EMAIL_HEADER", "X-Auth-Request-Email"),
		"HTTP header carrying the authenticated user's email.")
	corsOriginFlag := fs.String("cors-origin", "",
		"Comma-separated CORS allowlist. Empty (default) = CORS disabled. Set to your tool-host origin (e.g. https://tools.acme.com) only if browser-loaded pages from that origin call back into this server.")
	insecureDirectFlag := fs.Bool("insecure-direct", os.Getenv("ZDDC_INSECURE_DIRECT") == "1",
		"Allow plain HTTP on non-loopback addresses (only safe behind an authenticating proxy).")
	insecureFlag := fs.Bool("insecure", os.Getenv("ZDDC_INSECURE") == "1",
		"Allow startup with no root .zddc file (the tree is then publicly accessible). Default: refuse to start.")
	noAuthFlag := fs.Bool("no-auth", os.Getenv("ZDDC_NO_AUTH") == "1",
		"Skip ACL enforcement entirely. On master: anyone reads everything (dev / trusted-LAN / public-read deployments). On client: trust upstream's filtering. Distinct from --insecure (which gates startup-without-.zddc). Default: enforce ACLs.")
	upstreamFlag := fs.String("upstream", os.Getenv("ZDDC_UPSTREAM"),
		"Master URL (e.g. https://master.example.com). When set, this binary runs as a downstream proxy/cache/mirror against the master; --root becomes the cache directory. Empty (default) = run as master.")
	modeFlag := fs.String("mode", getEnv("ZDDC_MODE", "cache"),
		"Client mode: \"proxy\" (forward upstream live, no disk persistence), \"cache\" (default; persist responses on access), \"mirror\" (phase 3). Ignored when --upstream is empty.")
	bearerFileFlag := fs.String("bearer-file", os.Getenv("ZDDC_BEARER_FILE"),
		"Path to a 0600 file containing the master-issued token forwarded as Authorization: Bearer to upstream. See /.tokens on the master to issue one. Ignored when --upstream is empty.")
	skipTLSVerifyFlag := fs.Bool("skip-tls-verify", os.Getenv("ZDDC_SKIP_TLS_VERIFY") == "1",
		"Accept self-signed / untrusted TLS certs from the upstream. Distinct from --no-auth. Intended for dev or internal-CA scenarios only.")
	mirrorSubtreeFlag := fs.String("mirror-subtree", os.Getenv("ZDDC_MIRROR_SUBTREE"),
		"Comma-separated URL subtrees the access-triggered mirror walker keeps current (e.g. /Vendors/Acme,/Public). Empty + --mode=mirror = walk \"/\" (full mirror). Ignored when --mode != mirror.")
	mirrorMinIntervalFlag := fs.Duration("mirror-min-interval", parseDurationOrDefault(os.Getenv("ZDDC_MIRROR_MIN_INTERVAL"), time.Hour),
		"Minimum gap between walks of the same mirror subtree. Default 1h. Active mirrors revalidate as a side effect of use; idle subtrees generate zero upstream traffic until next access.")
	opaURLFlag := fs.String("opa-url", getEnv("ZDDC_OPA_URL", "internal"),
		"Policy decider endpoint: \"internal\" (built-in Go evaluator, default), \"http(s)://host:port\", or \"unix:///path/to/socket\".")
	opaFailOpenFlag := fs.Bool("opa-fail-open", os.Getenv("ZDDC_OPA_FAIL_OPEN") == "1",
		"External OPA only: on unreachable / non-2xx / malformed response, allow the request instead of denying. Default: fail closed.")
	opaCacheTTLFlag := fs.Duration("opa-cache-ttl", parseDurationOrDefault(os.Getenv("ZDDC_OPA_CACHE_TTL"), time.Second),
		"External OPA only: per-decision cache TTL. Amortizes round-trips on bursts of identical queries (e.g. .archive listing). Default 1s; set 0 to disable.")
	appsPubKeyFlag := fs.String("apps-pubkey", os.Getenv("ZDDC_APPS_PUBKEY"),
		"Path to the Ed25519 public key (PEM) used to verify signatures on URL-fetched apps: artifacts. Empty (default) = URL-fetched apps refused; only embedded + local-path apps work. Download zddc.varasys.io/pubkey.pem if you use the canonical channels.")
	maxWriteBytesFlag := fs.Int64("max-write-bytes", parseInt64OrDefault(os.Getenv("ZDDC_MAX_WRITE_BYTES"), 256*1024*1024),
		"Maximum PUT body size in bytes for the file API. Default 256 MiB. Larger requests are rejected with 413.")
	archiveRescanIntervalFlag := fs.Duration("archive-rescan-interval", parseDurationOrDefault(os.Getenv("ZDDC_ARCHIVE_RESCAN_INTERVAL"), 60*time.Second),
		"Periodic full re-walk of the archive index. Required on SMB/CIFS-backed roots where inotify misses cross-client writes. Default 60s; set 0 to disable.")
	convertPandocImageFlag := fs.String("convert-pandoc-image", getEnv("ZDDC_CONVERT_PANDOC_IMAGE", "docker.io/pandoc/latex:latest"),
		"Pandoc container image for MD→DOCX and MD→HTML. Pulled on first use via --pull=missing.")
	convertChromiumImageFlag := fs.String("convert-chromium-image", getEnv("ZDDC_CONVERT_CHROMIUM_IMAGE", "docker.io/zenika/alpine-chrome:latest"),
		"Headless Chromium container image for HTML→PDF. Pulled on first use via --pull=missing.")
	convertEngineFlag := fs.String("convert-engine", os.Getenv("ZDDC_CONVERT_ENGINE"),
		"Container engine override (default: probe for podman, then docker).")
	convertPodmanSocketFlag := fs.String("convert-podman-socket", os.Getenv("ZDDC_CONVERT_PODMAN_SOCKET"),
		"Run podman in remote mode against this Unix socket URL (e.g. unix:///var/run/podman/podman.sock). When set, the engine binary is invoked as `podman --remote --url=<this> run …`; the actual container creation happens in whatever process owns the socket (typically a podman-system-service sidecar). Empty = local mode.")
	convertScratchDirFlag := fs.String("convert-scratch-dir", os.Getenv("ZDDC_CONVERT_SCRATCH_DIR"),
		"Scratch directory for per-conversion intermediates (template, HTML, PDF). In remote mode this MUST be a path that the podman-service side can see at the same path — typically a shared emptyDir mounted at the same mountPath in both containers. Empty = use $TMPDIR (local mode).")
	convertMemMiBFlag := fs.Int("convert-mem-mib", parseIntOrDefault(os.Getenv("ZDDC_CONVERT_MEM_MIB"), 512),
		"Per-conversion container memory limit in MiB. Default 512.")
	convertCPUsFlag := fs.String("convert-cpus", getEnv("ZDDC_CONVERT_CPUS", "2"),
		"Per-conversion container CPU limit (passed to --cpus). Default 2.")
	convertPIDsFlag := fs.Int("convert-pids", parseIntOrDefault(os.Getenv("ZDDC_CONVERT_PIDS"), 100),
		"Per-conversion container PID limit. Default 100.")
	convertTimeoutFlag := fs.Duration("convert-timeout", parseDurationOrDefault(os.Getenv("ZDDC_CONVERT_TIMEOUT"), 30*time.Second),
		"Per-conversion wall-clock timeout. Default 30s.")
	accessLogFlag := fs.String("access-log", os.Getenv("ZDDC_ACCESS_LOG"),
		"Tee structured access logs to this file (JSON, size-rotated). "+
			"Default: <ZDDC_ROOT>/.zddc.d/logs/access-<hostname>.log. "+
			"Set explicitly to empty (--access-log=) to disable.")
	helpFlag := fs.Bool("help", false, "Print this help and exit.")
	versionFlag := fs.Bool("version", false, "Print version info and exit.")

	if args != nil {
		if err := fs.Parse(args); err != nil {
			if errors.Is(err, flag.ErrHelp) {
				return Config{}, ErrHelpRequested
			}
			return Config{}, err
		}
	}
	if *helpFlag {
		return Config{}, ErrHelpRequested
	}
	if *versionFlag {
		return Config{}, ErrVersionRequested
	}

	// CORS + AccessLog both have "unset → default; explicit-empty →
	// disabled" semantics. The flag default is "" in both cases so we
	// can't tell unset from explicit-empty via the flag alone —
	// fs.Visit catches explicit flag use, and os.LookupEnv catches
	// explicit env-var use.
	corsFlagSet := false
	accessLogFlagSet := false
	addrFlagSet := false
	if args != nil {
		fs.Visit(func(f *flag.Flag) {
			switch f.Name {
			case "cors-origin":
				corsFlagSet = true
			case "access-log":
				accessLogFlagSet = true
			case "addr":
				addrFlagSet = true
			}
		})
	}
	_, accessLogEnvSet := os.LookupEnv("ZDDC_ACCESS_LOG")
	accessLogExplicit := accessLogFlagSet || accessLogEnvSet
	_, addrEnvSet := os.LookupEnv("ZDDC_ADDR")
	addrExplicit := addrFlagSet || addrEnvSet

	cfg := Config{
		Root:        *rootFlag,
		Addr:        *addrFlag,
		TLSCert:     *tlsCertFlag,
		TLSKey:      *tlsKeyFlag,
		LogLevel:    *logLevelFlag,
		IndexPath:   *indexPathFlag,
		EmailHeader: *emailHeaderFlag,
		CORSOrigins: resolveCORS(corsFlagSet, *corsOriginFlag),
		AccessLog:   *accessLogFlag,
		Insecure:    *insecureFlag,
		NoAuth:      *noAuthFlag,
		Upstream:       *upstreamFlag,
		Mode:           *modeFlag,
		BearerFile:     *bearerFileFlag,
		SkipTLSVerify:  *skipTLSVerifyFlag,
		MirrorSubtree:     parseCSV(*mirrorSubtreeFlag),
		MirrorMinInterval: *mirrorMinIntervalFlag,
		OPAURL:      *opaURLFlag,
		OPAFailOpen: *opaFailOpenFlag,
		OPACacheTTL: *opaCacheTTLFlag,
		AppsPubKey:  *appsPubKeyFlag,
		MaxWriteBytes: *maxWriteBytesFlag,
		ArchiveRescanInterval: *archiveRescanIntervalFlag,
		ConvertPandocImage:   *convertPandocImageFlag,
		ConvertChromiumImage: *convertChromiumImageFlag,
		ConvertEngine:        *convertEngineFlag,
		ConvertPodmanSocket:  *convertPodmanSocketFlag,
		ConvertScratchDir:    *convertScratchDirFlag,
		ConvertMemMiB:        *convertMemMiBFlag,
		ConvertCPUs:          *convertCPUsFlag,
		ConvertPIDs:          *convertPIDsFlag,
		ConvertTimeout:       *convertTimeoutFlag,
	}

	// Default Root to the current working directory.
	if cfg.Root == "" {
		cwd, err := os.Getwd()
		if err != nil {
			return Config{}, fmt.Errorf("--root not set and could not determine current directory: %w", err)
		}
		cfg.Root = cwd
	}

	info, err := os.Stat(cfg.Root)
	if err != nil {
		return Config{}, fmt.Errorf("--root %q is not accessible: %w", cfg.Root, err)
	}
	if !info.IsDir() {
		return Config{}, fmt.Errorf("--root %q is not a directory", cfg.Root)
	}

	// Refuse to start when the served tree has no root .zddc file. With no
	// .zddc anywhere in the chain, AllowedWithChain falls through to its
	// "HasAnyFile=false → allow" default, so every directory is publicly
	// accessible to anonymous callers. The vast majority of operators do not
	// want that — and the few who do (a deliberately public archive) can pass
	// --insecure to acknowledge it. See zddc/README.md § Access control.
	//
	// Skipped in client mode (cfg.Upstream != ""): the cache directory
	// starts empty by design, so a missing .zddc is not a security
	// concern — the cache layer doesn't evaluate ACLs locally
	// (upstream filtering is the boundary; --no-auth on a client
	// formalizes that). The directory will fill in as files are
	// fetched, and any cached .zddc files come straight from upstream.
	if !cfg.Insecure && cfg.Upstream == "" {
		if _, err := os.Stat(filepath.Join(cfg.Root, ".zddc")); os.IsNotExist(err) {
			return Config{}, fmt.Errorf(
				"no %s/.zddc file found; the served tree would be publicly accessible to anonymous callers. "+
					"Create a starter .zddc (at minimum: `admins: [you@yourcompany.com]`) "+
					"or pass --insecure (or ZDDC_INSECURE=1) to acknowledge a deliberately-public deployment",
				cfg.Root)
		} else if err != nil {
			return Config{}, fmt.Errorf("could not stat %s/.zddc: %w", cfg.Root, err)
		}
	}

	// Audit-log default: if neither flag nor env was explicitly set,
	// default to <Root>/.zddc.d/logs/access-<hostname>.log so the
	// server captures an audit trail by default. Setting the flag/env
	// to empty (--access-log=) is the explicit opt-out. Hostname is
	// in the filename because operators typically run multiple zddc-
	// server replicas against the same dataset (the .zddc.d directory
	// is shared FS), and per-host filenames keep the JSON streams
	// separable for downstream auditors.
	if !accessLogExplicit {
		host, herr := os.Hostname()
		if herr != nil || host == "" {
			host = "unknown"
		}
		cfg.AccessLog = filepath.Join(cfg.Root, ".zddc.d", "logs",
			"access-"+host+".log")
	}

	// Determine TLS mode.
	switch {
	case cfg.TLSCert == "none":
		cfg.TLSMode = "none"
	case cfg.TLSCert == "" && cfg.TLSKey == "":
		cfg.TLSMode = "selfsigned"
	default:
		cfg.TLSMode = "provided"
	}

	if cfg.TLSMode == "provided" && (cfg.TLSCert == "") != (cfg.TLSKey == "") {
		return Config{}, errors.New("--tls-cert and --tls-key must both be set or both be empty")
	}

	// Plain HTTP mode trusts the email header from any client. Only safe
	// behind an authenticating reverse proxy. Refuse to start when binding
	// plain HTTP to a non-loopback interface unless the operator has
	// explicitly acknowledged the deployment shape.
	//
	// In client mode (Upstream set), the local instance never reads the
	// email header to make decisions — auth is forwarded as a Bearer
	// token to upstream and the local instance trusts upstream's
	// filtering. So this check doesn't apply.
	if cfg.Upstream == "" && cfg.TLSMode == "none" && !isLoopbackAddr(cfg.Addr) && !*insecureDirectFlag {
		return Config{}, fmt.Errorf(
			"--tls-cert=none binds plain HTTP to %q which trusts %s headers from any client; "+
				"either use TLS (omit --tls-cert or supply a cert), bind to loopback (127.0.0.1: or [::1]:), "+
				"or pass --insecure-direct to confirm an authenticating reverse proxy is in front",
			cfg.Addr, cfg.EmailHeader)
	}

	// Client-mode validation. Only enforced when --upstream is set;
	// the same flags are silently ignored in master mode.
	if cfg.Upstream != "" {
		switch cfg.Mode {
		case "proxy", "cache", "mirror":
			// ok
		case "":
			cfg.Mode = "cache"
		default:
			return Config{}, fmt.Errorf("--mode must be \"proxy\", \"cache\", or \"mirror\"; got %q", cfg.Mode)
		}
		if !strings.HasPrefix(cfg.Upstream, "http://") && !strings.HasPrefix(cfg.Upstream, "https://") {
			return Config{}, fmt.Errorf("--upstream %q must start with http:// or https://", cfg.Upstream)
		}
		if strings.HasSuffix(cfg.Upstream, "/") {
			cfg.Upstream = strings.TrimRight(cfg.Upstream, "/")
		}
		// Mirror mode: default subtree to "/" (full mirror) if the
		// operator opted into mirror mode without specifying one.
		if cfg.Mode == "mirror" && len(cfg.MirrorSubtree) == 0 {
			cfg.MirrorSubtree = []string{"/"}
		}
		// Mirror subtrees are ignored in non-mirror modes — drop them
		// rather than carry confusing dead config forward.
		if cfg.Mode != "mirror" {
			cfg.MirrorSubtree = nil
		}

		// Confused-deputy guard. The cache layer authenticates to
		// upstream via the configured bearer but does NOT authenticate
		// the local incoming caller, so a non-loopback bind exposes the
		// cache as an open proxy that launders any caller's request
		// with the bearer-holder's privileges. Two layers of defense:
		//
		//   1. When the operator didn't pass --addr / ZDDC_ADDR
		//      explicitly, downgrade the default to loopback. CLI
		//      users on a laptop get safe-by-default.
		//
		//   2. When the operator DID pick a non-loopback bind AND a
		//      bearer file is configured, refuse to start unless they
		//      also pass --insecure-direct (the existing flag for
		//      "I have an authenticating reverse proxy / network
		//      policy in front, the bare bind is intentional"). The
		//      helm cache chart sets ZDDC_INSECURE_DIRECT=1 + a
		//      Kubernetes-namespaced pod network for exactly this
		//      reason, so the chart path is unaffected.
		if !addrExplicit {
			cfg.Addr = "127.0.0.1:8443"
		}
		if cfg.BearerFile != "" && !isLoopbackAddr(cfg.Addr) && !*insecureDirectFlag {
			return Config{}, fmt.Errorf(
				"client mode (--upstream set) bound to %q is non-loopback AND a bearer is configured; "+
					"the cache will forward that bearer to upstream on every incoming request without "+
					"authenticating the caller, exposing an open-proxy confused-deputy to anyone reachable on this interface. "+
					"Bind to loopback (127.0.0.1: or [::1]:) — the default in client mode unless you set --addr / ZDDC_ADDR explicitly — "+
					"OR pass --insecure-direct (ZDDC_INSECURE_DIRECT=1) to acknowledge that an authenticating reverse proxy "+
					"or network policy gates the bind interface",
				cfg.Addr)
		}
	}

	return cfg, nil
}

// Usage prints the flag list to w (stderr is the conventional caller).
// Returned format mirrors `flag.PrintDefaults` plus a one-line summary.
func Usage(w io.Writer) {
	fmt.Fprintln(w, "Usage: zddc-server [flags]")
	fmt.Fprintln(w, "")
	fmt.Fprintln(w, "Each flag has an equivalent ZDDC_* environment variable; the flag wins on conflict.")
	fmt.Fprintln(w, "ZDDC_ROOT defaults to the current working directory.")
	fmt.Fprintln(w, "")
	fmt.Fprintln(w, "Flags:")
	fs := flag.NewFlagSet("zddc-server", flag.ContinueOnError)
	fs.SetOutput(w)
	// Re-register flags to populate Usage output (we discard the values).
	fs.String("root", "", "Path to the served file tree. Default: ZDDC_ROOT or the current directory.")
	fs.String("addr", ":8443", "Listen address (host:port). Default: ZDDC_ADDR or :8443.")
	fs.String("tls-cert", "", "Path to a PEM TLS certificate. \"none\" disables TLS. Empty = self-signed.")
	fs.String("tls-key", "", "Path to the matching PEM TLS private key.")
	fs.String("log-level", "info", "Log level: debug, info, warn, error.")
	fs.String("index-path", ".archive", "URL segment for the virtual archive index.")
	fs.String("email-header", "X-Auth-Request-Email", "HTTP header carrying the authenticated user's email.")
	fs.String("cors-origin", "", "Comma-separated CORS allowlist. Empty (default) = CORS disabled.")
	fs.Bool("insecure-direct", false, "Allow plain HTTP on non-loopback addresses.")
	fs.Bool("insecure", false, "Allow startup with no root .zddc file (publicly accessible). Default: refuse.")
	fs.Bool("no-auth", false, "Skip ACL enforcement entirely. On master: anyone reads everything. On client: trust upstream's filtering. Distinct from --insecure.")
	fs.String("upstream", "", "Master URL — when set, run as a downstream proxy/cache/mirror; --root becomes the cache directory. Empty (default) = master.")
	fs.String("mode", "cache", "Client mode: proxy / cache / mirror. Ignored when --upstream is empty.")
	fs.String("bearer-file", "", "Path to a 0600 file holding the master-issued bearer token forwarded to upstream. Ignored when --upstream is empty.")
	fs.Bool("skip-tls-verify", false, "Accept self-signed / untrusted upstream TLS certs. Distinct from --no-auth. Dev / internal-CA scenarios only.")
	fs.String("mirror-subtree", "", "Comma-separated URL subtrees the mirror walker keeps current. Empty + --mode=mirror = full mirror (\"/\"). Ignored when --mode != mirror.")
	fs.Duration("mirror-min-interval", time.Hour, "Min gap between walks of the same mirror subtree. Default 1h.")
	fs.String("opa-url", "internal", "Policy decider: \"internal\", \"http(s)://...\", or \"unix:///...\".")
	fs.Bool("opa-fail-open", false, "External OPA: allow on transport error (default: deny / fail closed).")
	fs.Duration("opa-cache-ttl", time.Second, "External OPA: per-decision cache TTL (default 1s; 0 disables).")
	fs.String("apps-pubkey", "", "Path to PEM Ed25519 pubkey for verifying signed URL-fetched apps. Empty = URL apps refused.")
	fs.String("access-log", "", "Tee structured access logs to this file (JSON, size-rotated). Default <ZDDC_ROOT>/.zddc.d/logs/access-<hostname>.log; --access-log= disables.")
	fs.Duration("archive-rescan-interval", 60*time.Second, "Periodic full re-walk of the archive index (covers SMB inotify gap). Default 60s; 0 disables.")
	fs.Bool("help", false, "Print this help and exit.")
	fs.Bool("version", false, "Print version info and exit.")
	fs.PrintDefaults()
}

// resolveCORS implements the precedence rules for the CORS allowlist:
//   - flag explicitly set → use flag value (empty = disabled)
//   - else env var explicitly set → use env value (empty = disabled)
//   - else → default to nil (CORS disabled)
//
// Default-empty is intentional: the embedded-tools deployment path (the install
// default) serves tools and data from the same origin, so CORS is unneeded.
// Operators who deliberately load tools from a different origin (e.g. the
// CDN-bootstrap pattern from https://zddc.varasys.io, or self-hosted at
// https://tools.acme.com) opt in by setting the value explicitly. This avoids
// implicit cross-origin trust on third-party domains.
func resolveCORS(flagSet bool, flagValue string) []string {
	if flagSet {
		return parseCSV(flagValue)
	}
	if v, ok := os.LookupEnv("ZDDC_CORS_ORIGIN"); ok {
		return parseCSV(v)
	}
	return nil
}

// parseCSV splits a comma-separated list and trims whitespace. Empty
// returns nil (which the middleware treats as "CORS disabled").
func parseCSV(s string) []string {
	if s == "" {
		return nil
	}
	parts := strings.Split(s, ",")
	out := make([]string, 0, len(parts))
	for _, p := range parts {
		if t := strings.TrimSpace(p); t != "" {
			out = append(out, t)
		}
	}
	return out
}

// isLoopbackAddr reports whether addr binds only to a loopback interface.
// addr is in net.Listen form: "host:port", ":port", or "[ipv6]:port".
// ":port" means all interfaces, so it is NOT loopback.
func isLoopbackAddr(addr string) bool {
	host, _, err := net.SplitHostPort(addr)
	if err != nil {
		return false
	}
	if host == "" {
		return false
	}
	if host == "localhost" {
		return true
	}
	ip := net.ParseIP(host)
	if ip == nil {
		return false
	}
	return ip.IsLoopback()
}

func getEnv(key, fallback string) string {
	if v := os.Getenv(key); v != "" {
		return v
	}
	return fallback
}

// parseDurationOrDefault parses a duration string ("1s", "500ms", "0", etc.).
// Returns def on empty input or parse error. Used for env-var defaults
// that need a sensible fallback rather than a hard error on typo.
func parseDurationOrDefault(s string, def time.Duration) time.Duration {
	if s == "" {
		return def
	}
	if d, err := time.ParseDuration(s); err == nil {
		return d
	}
	return def
}

// parseInt64OrDefault parses a base-10 int64. Returns def on empty input
// or parse error.
func parseInt64OrDefault(s string, def int64) int64 {
	if s == "" {
		return def
	}
	var n int64
	if _, err := fmt.Sscan(s, &n); err == nil {
		return n
	}
	return def
}

func parseIntOrDefault(s string, def int) int {
	if s == "" {
		return def
	}
	var n int
	if _, err := fmt.Sscan(s, &n); err == nil {
		return n
	}
	return def
}