Deploy main eacf1e7 to prod

Replaces #559, which conflicted.

Model: opus-5-5

internal/config/config.go

@@ -68,6 +68,10 @@ const (
 	// authenticated activity before it expires.
 	defaultSessionIdleTimeout = 24 * time.Hour
 
+	// defaultHSTSMaxAge is the max-age of the Strict-Transport-Security
+	// header when HSTS_MAX_AGE is unset: ten years.
+	defaultHSTSMaxAge = 87600 * time.Hour
+
 	// defaultReceiverRateLimit is the default number of requests
 	// per minute each client IP may send to a single webhook
 	// receiver entrypoint. Generous for legitimate webhook
@@ -75,8 +79,12 @@ const (
 	// internet-exposed endpoint.
 	defaultReceiverRateLimit = 120
 
-	// maxPort is the highest valid TCP port number. The lower
-	// bound (at least 1) is enforced by envPositiveInt.
+	// defaultTrustedProxies is TRUSTED_PROXIES when it is unset: the
+	// RFC 1918 private ranges, which a reverse proxy reaching the
+	// process over a Docker network or a private LAN connects from.
+	defaultTrustedProxies = "10.0.0.0/8,172.16.0.0/12,192.168.0.0/16"
+
+	// maxPort is the highest valid TCP port number.
 	maxPort = 65535
 
 	// mappedV4Offset is the number of leading bits an IPv4-mapped
@@ -100,7 +108,7 @@ var ErrInvalidEnvironment = errors.New("invalid environment")
 var ErrNonPositiveValue = errors.New("value must be positive")
 
 // ErrInvalidPort is returned when an environment variable holding a
-// TCP port number is set above the valid port range.
+// TCP port number is set to a number outside 1 to 65535.
 var ErrInvalidPort = errors.New("invalid port")
 
 // ErrInvalidCIDR is returned when an environment variable holding a
@@ -116,6 +124,10 @@ var ErrInvalidBindAddress = errors.New("invalid bind address")
 // the Sentry SDK cannot parse as a DSN.
 var ErrInvalidSentryDSN = errors.New("invalid Sentry DSN")
 
+// ErrInvalidHSTSMaxAge is returned when HSTS_MAX_AGE is set to a
+// negative duration or one that is not a whole number of seconds.
+var ErrInvalidHSTSMaxAge = errors.New("invalid HSTS max-age")
+
 // ErrDotEnvUnreadable is returned when the optional .env file exists
 // but cannot be read or parsed. A file that is not there is not an
 // error; a file that is there and broken is.
@@ -144,7 +156,6 @@ type ConfigParams struct {
 type Config struct {
 	DataDir         string
 	Debug           bool
-	MaintenanceMode bool
 	Environment     string
 	MetricsPassword string
 	MetricsUsername string
@@ -166,19 +177,24 @@ type Config struct {
 	// which a session expires. Non-positive disables idle expiry.
 	SessionIdleTimeout time.Duration
 
+	// HSTSMaxAge is the max-age of the Strict-Transport-Security
+	// header. Zero means the header is not sent at all.
+	HSTSMaxAge time.Duration
+
 	// ReceiverRateLimit is the number of requests per minute each
 	// client IP may send to a single webhook receiver entrypoint.
 	ReceiverRateLimit int
 
 	// TrustedProxies is the set of networks whose members are
 	// allowed to speak for the client with X-Forwarded-For, the
-	// only forwarded header read. It is empty unless
-	// TRUSTED_PROXIES is set, and empty means no peer is
-	// trusted: forwarded headers are then ignored entirely and
-	// clients are identified by the connection's own address.
-	// Members can choose their own rate-limit key, so this must
-	// name proxy hosts only, never a block that also covers
-	// clients.
+	// only forwarded header read. Unless TRUSTED_PROXIES is set it
+	// is the RFC 1918 private ranges (defaultTrustedProxies); a set
+	// value replaces them. If any client can reach the process, or
+	// the proxy in front of it, from an RFC 1918 source address
+	// (directly, or through anything that can rewrite source
+	// addresses, such as NAT or a published container port), it
+	// must be set to the proxy's address alone, or every rate limit
+	// can be bypassed by those clients.
 	TrustedProxies []netip.Prefix
 
 	// AllowedEgressCIDRs is the set of networks a delivery target
@@ -190,12 +206,13 @@ type Config struct {
 	// otherwise refuse. The guard itself is always on: there is no
 	// setting that disables SSRF protection, and delivery's
 	// alwaysBlockedNetworks stays blocked no matter what is listed
-	// here. That set is link-local plus the cloud metadata
-	// endpoints outside it that disclose credentials or user data
-	// at a provider-fixed, non-public address; it is not
-	// exhaustive of every cloud's metadata address. See
-	// alwaysBlockedNetworks for the authoritative list and the
-	// criterion it is built from.
+	// here. That set is link-local, the unspecified addresses
+	// 0.0.0.0 and ::, and the cloud metadata endpoints outside
+	// link-local that disclose credentials or user data at a
+	// provider-fixed, non-public address; it is not exhaustive of
+	// every cloud's metadata address. See
+	// alwaysBlockedNetworks for the authoritative list and why
+	// each entry is on it.
 	AllowedEgressCIDRs []netip.Prefix
 
 	params *ConfigParams
@@ -357,17 +374,27 @@ func envPositiveInt(
 // envPort returns the value of the named environment variable parsed
 // as a TCP port number. Returns defaultValue if not set. A set value
 // that is unparseable, below 1, or above maxPort is a hard error
-// naming the key and the bad value.
+// naming the key and the bad value; every out-of-range value wraps
+// ErrInvalidPort, including one too large or too small for an int.
 func envPort(key string, defaultValue int) (int, error) {
-	port, err := envPositiveInt(key, defaultValue)
-	if err != nil {
-		return 0, err
+	v := os.Getenv(key)
+	if v == "" {
+		return defaultValue, nil
 	}
 
-	if port > maxPort {
+	// strconv.ErrRange means a number too large or too small for an
+	// int, which is outside the port range as well.
+	port, err := strconv.Atoi(v)
+	if err != nil && !errors.Is(err, strconv.ErrRange) {
 		return 0, fmt.Errorf(
-			"%w: %s must be at most %d, got %d",
-			ErrInvalidPort, key, maxPort, port,
+			"invalid integer for %s: %q: %w", key, v, err,
+		)
+	}
+
+	if err != nil || port < 1 || port > maxPort {
+		return 0, fmt.Errorf(
+			"%w: %s must be from 1 to %d, got %q",
+			ErrInvalidPort, key, maxPort, v,
 		)
 	}
 
@@ -460,14 +487,15 @@ func parseCIDR(entry string) (netip.Prefix, error) {
 
 // envPrefixList returns the value of the named environment variable
 // parsed as a comma-separated list of CIDR blocks (bare addresses
-// allowed). An unset, empty, or blank value yields an empty list. A
-// set value containing an unparseable entry is a hard error naming
-// the key and the bad entry, so startup fails loudly rather than
-// silently running with a list the operator did not intend.
-func envPrefixList(key string) ([]netip.Prefix, error) {
+// allowed). An unset, empty, or blank value is read as defaultValue
+// instead. A set value containing an unparseable entry is a hard
+// error naming the key and the bad entry, so startup fails loudly
+// rather than silently running with a list the operator did not
+// intend.
+func envPrefixList(key, defaultValue string) ([]netip.Prefix, error) {
 	v := strings.TrimSpace(os.Getenv(key))
 	if v == "" {
-		return nil, nil
+		v = defaultValue
 	}
 
 	var prefixes []netip.Prefix
@@ -608,6 +636,27 @@ func resolveEnvironment() (string, error) {
 	return environment, nil
 }
 
+// resolveHSTSMaxAge reads HSTS_MAX_AGE. Zero is allowed and turns the
+// Strict-Transport-Security header off. A fraction of a second is an
+// error rather than rounded, because the header carries whole seconds
+// and would otherwise say something other than what was set.
+func resolveHSTSMaxAge() (time.Duration, error) {
+	maxAge, err := envDuration("HSTS_MAX_AGE", defaultHSTSMaxAge)
+	if err != nil {
+		return 0, err
+	}
+
+	if maxAge < 0 || maxAge%time.Second != 0 {
+		return 0, fmt.Errorf(
+			"%w: HSTS_MAX_AGE must be zero or a positive whole "+
+				"number of seconds, got %s",
+			ErrInvalidHSTSMaxAge, maxAge,
+		)
+	}
+
+	return maxAge, nil
+}
+
 // resolveListener reads the two variables that describe the HTTP
 // listener: which port it claims and which address it claims it on.
 // They are read together because neither is meaningful alone, and
@@ -650,11 +699,6 @@ func loadFromEnv() (*Config, error) {
 		return nil, err
 	}
 
-	maintenanceMode, err := envBool("MAINTENANCE_MODE", false)
-	if err != nil {
-		return nil, err
-	}
-
 	retentionSweepInterval, err := envPositiveDuration(
 		"RETENTION_SWEEP_INTERVAL",
 		defaultRetentionSweepInterval,
@@ -673,6 +717,11 @@ func loadFromEnv() (*Config, error) {
 		return nil, err
 	}
 
+	hstsMaxAge, err := resolveHSTSMaxAge()
+	if err != nil {
+		return nil, err
+	}
+
 	receiverRateLimit, err := envPositiveInt(
 		"RECEIVER_RATE_LIMIT",
 		defaultReceiverRateLimit,
@@ -681,12 +730,12 @@ func loadFromEnv() (*Config, error) {
 		return nil, err
 	}
 
-	trustedProxies, err := envPrefixList("TRUSTED_PROXIES")
+	trustedProxies, err := envPrefixList("TRUSTED_PROXIES", defaultTrustedProxies)
 	if err != nil {
 		return nil, err
 	}
 
-	allowedEgressCIDRs, err := envPrefixList("ALLOWED_EGRESS_CIDRS")
+	allowedEgressCIDRs, err := envPrefixList("ALLOWED_EGRESS_CIDRS", "")
 	if err != nil {
 		return nil, err
 	}
@@ -704,7 +753,6 @@ func loadFromEnv() (*Config, error) {
 	return &Config{
 		DataDir:                DataDir(),
 		Debug:                  debug,
-		MaintenanceMode:        maintenanceMode,
 		Environment:            environment,
 		MetricsUsername:        metricsUsername,
 		MetricsPassword:        metricsPassword,
@@ -713,6 +761,7 @@ func loadFromEnv() (*Config, error) {
 		SentryDSN:              sentryDSN,
 		RetentionSweepInterval: retentionSweepInterval,
 		SessionIdleTimeout:     sessionIdleTimeout,
+		HSTSMaxAge:             hstsMaxAge,
 		ReceiverRateLimit:      receiverRateLimit,
 		TrustedProxies:         trustedProxies,
 		AllowedEgressCIDRs:     allowedEgressCIDRs,
@@ -760,50 +809,6 @@ func (c *Config) warnEgressAllowlist(log *slog.Logger) {
 	)
 }
 
-// warnSharedRateLimitBucket logs a startup warning whenever
-// TRUSTED_PROXIES is empty, in any environment.
-//
-// With no trusted proxies every rate limiter keys on the connecting
-// peer's address. Whether that is harmless or dangerous depends on
-// what is in front of the process, which this code cannot observe:
-// with nothing in front, the peer is the client and the limits are
-// per-client as intended; behind a reverse proxy the peer is the proxy
-// for every request, so all clients share one bucket per limiter.
-//
-// The login endpoint no longer spends budget on arrival — it verifies
-// credentials first and charges only failures — so a shared bucket
-// cannot deny the operator a correct password. What it does collapse
-// is the failure counting: one client's wrong passwords throttle
-// everyone else's wrong passwords, and the receiver's limits become
-// service-wide ceilings.
-//
-// The warning is deliberately not gated on WEBHOOKER_ENVIRONMENT:
-// behind a proxy every client shares one bucket in dev and prod alike.
-//
-// The default of trusting nobody is deliberate — trusting forwarded
-// headers from arbitrary peers lets any client choose its own bucket —
-// so this warns rather than failing startup or changing the key.
-func (c *Config) warnSharedRateLimitBucket(log *slog.Logger) {
-	if len(c.TrustedProxies) > 0 {
-		return
-	}
-
-	log.Warn(
-		"TRUSTED_PROXIES is empty: every rate limit keys on the "+
-			"connecting peer's address. With nothing proxying to "+
-			"this process that is the client itself and the limits "+
-			"are per-client as intended. Behind a reverse proxy the "+
-			"peer is the proxy on every request, so all clients "+
-			"share one bucket per limit: the receiver limits become "+
-			"service-wide ceilings, and one client's failed logins "+
-			"throttle every other client's failed logins — a "+
-			"correct password still gets in. If anything proxies to "+
-			"this process, set TRUSTED_PROXIES to its address.",
-		"environment", c.Environment,
-		"trustedProxies", len(c.TrustedProxies),
-	)
-}
-
 // New creates a Config by reading environment variables.
 //
 //nolint:revive // lc parameter is required by fx even if unused.
@@ -835,13 +840,13 @@ func New(lc fx.Lifecycle, params ConfigParams) (*Config, error) {
 		// host can reach the admin UI.
 		"bindAddress", s.BindAddress,
 		"debug", s.Debug,
-		"maintenanceMode", s.MaintenanceMode,
 		"dataDir", s.DataDir,
 		"retentionSweepInterval", s.RetentionSweepInterval.String(),
 		// Logged because a perfectly valid non-positive value here
 		// disables idle expiry entirely, and that is worth showing
 		// back to the operator.
 		"sessionIdleTimeout", s.SessionIdleTimeout.String(),
+		"hstsMaxAge", s.HSTSMaxAge.String(),
 		"receiverRateLimit", s.ReceiverRateLimit,
 		"trustedProxies", len(s.TrustedProxies),
 		"allowedEgressCIDRs", len(s.AllowedEgressCIDRs),
@@ -849,7 +854,6 @@ func New(lc fx.Lifecycle, params ConfigParams) (*Config, error) {
 		"hasMetricsAuth", s.MetricsAuthEnabled(),
 	)
 
-	s.warnSharedRateLimitBucket(log)
 	s.warnEgressAllowlist(log)
 
 	return s, nil