fix(archreview): security authz+hub cluster (SEC-07/05/08/11) + validation hardening

SEC-07: add QueryActiveAlarmsRequest -> events:read scope arm; fix two tests that
  constructed StreamAlarmsRequest instead of QueryActiveAlarmsRequest.
SEC-05: shorten hub-token lifetime 30m -> 5m; document that the ?access_token= query
  carriage must never be request-logged.
SEC-08: gateway-side CachingApiKeyVerifier (short TTL, keyed on a hash of the presented
  secret) skips the per-call store read+last_used write; CoalescingMarkApiKeyStore bounds
  last_used writes to <=1/key/min; identity constraints are cached. Invalidation is wired
  at the gateway admin sites (revoke/rotate/delete); short TTL backstops out-of-process CLI.
SEC-11: fixed-window rate limit on POST /auth/login + a per-peer (key-id) failure limiter
  checked before VerifyAsync; new MxGateway:Security options bound + validated.

Also fixes regressions from the SEC-01/04/06 commit (c185f62) that a narrow test filter
missed (all now covered by a full-suite checkpoint):
- Rooting check is cross-platform: accepts Windows C:\/UNC forms on Unix so the shipped
  appsettings path validates on the macOS dev box, still rejecting bare filenames.
- AddGatewayConfiguration TryAdds a non-production IHostEnvironment fallback so the validator
  resolves in minimal test/tooling containers; the real host + apikey CLI register the actual
  environment first (TryAdd no-op there).
- Test assembly defaults ASPNETCORE_ENVIRONMENT=Development (ModuleInitializer) so full-host
  tests exercise wiring instead of tripping the SEC-04/06 production guards.
- GatewayOptionsTests asserts the SEC-01 CommonApplicationData-derived default (platform-correct).

archreview: SEC-07/05/08/11 (P1). Verified: NonWindows build clean; full gateway suite
747 passed / 42 failed, where all 42 are the pre-existing macOS named-pipe-harness failures
(Unix-socket path limit) and 0 are validation/regression failures.
This commit is contained in:
Joseph Doherty
2026-07-09 07:31:35 -04:00
parent 970613eebd
commit 17f16ea181
29 changed files with 1521 additions and 18 deletions
@@ -15,7 +15,8 @@ public sealed class GatewayGrpcAuthorizationInterceptor(
IApiKeyVerifier apiKeyVerifier,
GatewayGrpcScopeResolver scopeResolver,
IGatewayRequestIdentityAccessor identityAccessor,
IOptions<GatewayOptions> options) : Interceptor
IOptions<GatewayOptions> options,
ApiKeyFailureLimiter failureLimiter) : Interceptor
{
/// <inheritdoc />
public override async Task<TResponse> UnaryServerHandler<TRequest, TResponse>(
@@ -63,6 +64,19 @@ public sealed class GatewayGrpcAuthorizationInterceptor(
string? authorizationHeader = context.RequestHeaders.GetValue("authorization");
// SEC-11: short-circuit a peer that has already failed too many times inside the sliding
// window BEFORE the verification store read, so online guessing cannot spend a SQLite read
// per attempt. The peer key prefers the presented key id over the transport address (NAT
// caveat). ResourceExhausted signals throttling without revealing whether any particular
// secret was valid.
string peerKey = ResolvePeerKey(authorizationHeader, context);
if (failureLimiter.IsBlocked(peerKey))
{
throw new RpcException(new Status(
StatusCode.ResourceExhausted,
"Too many authentication attempts. Try again later."));
}
// The shared verifier owns parse + pepper + lookup + revocation + constant-time compare,
// returning a discriminated failure rather than throwing. Every authentication failure maps
// to Unauthenticated with an opaque message; the client never learns which stage failed.
@@ -72,11 +86,16 @@ public sealed class GatewayGrpcAuthorizationInterceptor(
if (!verification.Succeeded || verification.Identity is null)
{
failureLimiter.RecordFailure(peerKey);
throw new RpcException(new Status(
StatusCode.Unauthenticated,
"Missing or invalid API key."));
}
// Successful authentication clears the peer's failure count so a legitimate client that
// fat-fingered a few attempts is not penalised once it recovers.
failureLimiter.Reset(peerKey);
ApiKeyIdentity identity = GatewayApiKeyIdentityMapper.ToGatewayIdentity(verification.Identity);
string requiredScope = scopeResolver.ResolveRequiredScope(request);
@@ -89,4 +108,30 @@ public sealed class GatewayGrpcAuthorizationInterceptor(
return identity;
}
// Resolves the failure-limiter partition key: the presented key id (token shape
// mxgw_<keyId>_<secret>) when the header parses, otherwise the transport peer address. Keying on
// key id throttles a single abusive credential without locking out co-located clients behind NAT.
private static string ResolvePeerKey(string? authorizationHeader, ServerCallContext context)
{
if (!string.IsNullOrWhiteSpace(authorizationHeader))
{
ReadOnlySpan<char> header = authorizationHeader.AsSpan().Trim();
const string bearer = "Bearer ";
ReadOnlySpan<char> token = header.StartsWith(bearer, StringComparison.OrdinalIgnoreCase)
? header[bearer.Length..].Trim()
: header;
// mxgw_<keyId>_<secret>: the key id is the second underscore-delimited segment. The
// secret may itself contain underscores, but the key id is unaffected.
string tokenText = token.ToString();
string[] parts = tokenText.Split('_');
if (parts.Length >= 3 && parts[0].Length > 0 && parts[1].Length > 0)
{
return "key:" + parts[1];
}
}
return "peer:" + context.Peer;
}
}