agent: unify listening and dialing with directed mutual measurements

Replace Probe with Agent across node runtime, Fleet contracts, backend state, API and storage. Report incoming sessions and outgoing link health through each Agent uplink, and retain directed link controls and retry.

Update protocol fixtures and end-to-end coverage for the unified model; accept requested cancellation during the Fleet timeout test cleanup.
This commit is contained in:
justme committed 2026-10-21 11:55:36 +08:00
1 parent d5ebf29e57
commit ad5efc62ff
206 files changed
+4202 -4964

No files matched your search

+33 -33
View File
@@ -328,10 +328,10 @@ public sealed class LinkTests
public byte[] Spki => NodeCertificate.SpkiFingerprint(Certificate);
/// <summary>Agent 的 TLS 证书公钥:Probe 用它固定证书、派生敲门密钥。</summary>
/// <summary>Agent 的 TLS 证书公钥:拨号方 用它固定证书、派生敲门密钥。</summary>
public byte[] PublicKey => Certificate.PublicKey.ExportSubjectPublicKeyInfo();
/// <summary>名册:能敲开门的 Probe 公钥。</summary>
/// <summary>名册:能敲开门的 拨号方 公钥。</summary>
public List<byte[]> KnockPeers { get; } = [];
public async ValueTask DisposeAsync()
@@ -352,25 +352,25 @@ public sealed class LinkTests
}
[Fact]
public async Task PeerHandshake_AuthenticatesTheProbe_AndBothSidesDeriveTheSameDataPlaneCredentials()
public async Task PeerHandshake_AuthenticatesTheDialer_AndBothSidesDeriveTheSameDataPlaneCredentials()
{
using NodeIdentity probe = NodeIdentity.Generate();
using NodeIdentity dialer = NodeIdentity.Generate();
var seen = new TaskCompletionSource<PeerSessionInfo>();
await using var agent = new PeerFixture(id => id == "prb_1" ? probe.PublicKeySpki : null, (info, transport, ct) =>
await using var agent = new PeerFixture(id => id == "dlr_1" ? dialer.PublicKeySpki : null, (info, transport, ct) =>
{
seen.TrySetResult(info);
return Task.Delay(Timeout.Infinite, ct).ContinueWith(_ => { }, CancellationToken.None);
});
agent.KnockPeers.Add(probe.PublicKeySpki);
agent.KnockPeers.Add(dialer.PublicKeySpki);
await agent.Listener.Started.Task;
var logs = new Fleet.Hosting.BufferedNodeLog(NullNodeLog.Instance, TimeProvider.System);
var scoped = new ContextNodeLog(logs, ("attempt_id", "test-attempt"));
(PeerSessionInfo client, TlsFrameTransport transport) = await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, probe, "prb_1", null, 1 << 20, TimeProvider.System, scoped, default);
(PeerSessionInfo client, TlsFrameTransport transport) = await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, dialer, "dlr_1", null, 1 << 20, TimeProvider.System, scoped, default);
await using (transport)
{
PeerSessionInfo server = await seen.Task.WaitAsync(TimeSpan.FromSeconds(5));
Assert.Equal("prb_1", server.PeerId);
Assert.Equal("dlr_1", server.PeerId);
Assert.Equal(client.Credentials.Key, server.Credentials.Key);
Assert.Equal(client.Credentials.SessionId, server.Credentials.SessionId);
NodeLogBatch batch = logs.TakeBatch(32);
@@ -380,62 +380,62 @@ public sealed class LinkTests
}
[Fact]
public async Task PeerHandshake_RejectsUnknownProbes_AndForgedSignatures_WithTheSameError()
public async Task PeerHandshake_RejectsUnknownDialers_AndForgedSignatures_WithTheSameError()
{
using NodeIdentity probe = NodeIdentity.Generate();
using NodeIdentity dialer = NodeIdentity.Generate();
using NodeIdentity impostor = NodeIdentity.Generate();
await using var agent = new PeerFixture(id => id == "prb_1" ? probe.PublicKeySpki : null);
agent.KnockPeers.AddRange([probe.PublicKeySpki, impostor.PublicKeySpki]); // 敲门通过之后,名册外的 ID 和伪造的签名仍然被拒绝
await using var agent = new PeerFixture(id => id == "dlr_1" ? dialer.PublicKeySpki : null);
agent.KnockPeers.AddRange([dialer.PublicKeySpki, impostor.PublicKeySpki]); // 敲门通过之后,名册外的 ID 和伪造的签名仍然被拒绝
await agent.Listener.Started.Task;
var logs = new Fleet.Hosting.BufferedNodeLog(NullNodeLog.Instance, TimeProvider.System);
InvalidOperationException unknown = await Assert.ThrowsAsync<InvalidOperationException>(async () =>
await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, probe, "prb_unknown", null, 1 << 20, TimeProvider.System, logs, default));
await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, dialer, "dlr_unknown", null, 1 << 20, TimeProvider.System, logs, default));
NodeLogRecord failure = Assert.Single(logs.TakeBatch(32).Records, entry => entry.Message == "peer control handshake failed");
Assert.Equal("peer_auth", failure.Fields["phase"]);
Assert.Equal("InvalidOperationException", failure.Fields["exception"]);
InvalidOperationException forged = await Assert.ThrowsAsync<InvalidOperationException>(async () =>
await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, impostor, "prb_1", null, 1 << 20, TimeProvider.System, default));
await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, impostor, "dlr_1", null, 1 << 20, TimeProvider.System, default));
Assert.Equal(unknown.Message, forged.Message);
Assert.Contains("fleet_unauthorized", forged.Message);
// 正主仍然可以连接
(_, TlsFrameTransport ok) = await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, probe, "prb_1", null, 1 << 20, TimeProvider.System, default);
(_, TlsFrameTransport ok) = await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, dialer, "dlr_1", null, 1 << 20, TimeProvider.System, default);
await ok.DisposeAsync();
}
[Fact]
public async Task PeerHandshake_PinsTheAgentCertificate_ByItsSpkiFingerprint()
{
using NodeIdentity probe = NodeIdentity.Generate();
await using var agent = new PeerFixture(_ => probe.PublicKeySpki);
agent.KnockPeers.Add(probe.PublicKeySpki);
using NodeIdentity dialer = NodeIdentity.Generate();
await using var agent = new PeerFixture(_ => dialer.PublicKeySpki);
agent.KnockPeers.Add(dialer.PublicKeySpki);
await agent.Listener.Started.Task;
// 公钥不对:敲门密钥对不上,Agent 直接断开(拿到的不是证书,连不是它的证书都看不到)
using NodeIdentity another = NodeIdentity.Generate();
await Assert.ThrowsAnyAsync<Exception>(async () =>
await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, another.PublicKeySpki, probe, "prb_1", null, 1 << 20, TimeProvider.System, default));
await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, another.PublicKeySpki, dialer, "dlr_1", null, 1 << 20, TimeProvider.System, default));
}
[Fact]
public async Task PeerSession_CarriesRpcBothWays_AfterTheHandshake()
{
using NodeIdentity probe = NodeIdentity.Generate();
using NodeIdentity dialer = NodeIdentity.Generate();
MethodTable table = TestTables.Of(TestTables.Req("agent.echo"));
var router = new RpcRouter<string>(RpcSide.Listener, table).On("agent.echo", LinkJson.Default.Number, LinkJson.Default.Number, (_, p, _) => ValueTask.FromResult(Result<Number>.Ok(new Number { Value = p.Value + 1 })));
await using var agent = new PeerFixture(
_ => probe.PublicKeySpki,
_ => dialer.PublicKeySpki,
async (info, transport, ct) =>
{
await using var session = new RpcSession<string>(transport, router, info.PeerId, TimeProvider.System);
await session.RunAsync(ct);
});
agent.KnockPeers.Add(probe.PublicKeySpki);
agent.KnockPeers.Add(dialer.PublicKeySpki);
await agent.Listener.Started.Task;
(_, TlsFrameTransport transport) = await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, probe, "prb_1", null, 1 << 20, TimeProvider.System, default);
await using var client = new RpcSession<string>(transport, new RpcRouter<string>(RpcSide.Dialer, table), "probe", TimeProvider.System);
(_, TlsFrameTransport transport) = await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, dialer, "dlr_1", null, 1 << 20, TimeProvider.System, default);
await using var client = new RpcSession<string>(transport, new RpcRouter<string>(RpcSide.Dialer, table), "dialer", TimeProvider.System);
Task run = client.RunAsync(default);
Result<Number> result = await client.RequestAsync("agent.echo", new Number { Value = 41 }, LinkJson.Default.Number, LinkJson.Default.Number, default);
Assert.Equal(42, result.Value.Value);
@@ -446,9 +446,9 @@ public sealed class LinkTests
[Fact]
public async Task PeerListener_LimitsConcurrentSessions_AndSurvivesGarbageConnections()
{
using NodeIdentity probe = NodeIdentity.Generate();
await using var agent = new PeerFixture(_ => probe.PublicKeySpki);
agent.KnockPeers.Add(probe.PublicKeySpki);
using NodeIdentity dialer = NodeIdentity.Generate();
await using var agent = new PeerFixture(_ => dialer.PublicKeySpki);
agent.KnockPeers.Add(dialer.PublicKeySpki);
await agent.Listener.Started.Task;
// 不说 TLS 的连接:握手失败,监听继续
@@ -458,16 +458,16 @@ public sealed class LinkTests
await garbage.GetStream().WriteAsync("GET / HTTP/1.1\r\n\r\n"u8.ToArray());
}
(_, TlsFrameTransport ok) = await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, probe, "prb_1", null, 1 << 20, TimeProvider.System, default);
(_, TlsFrameTransport ok) = await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, dialer, "dlr_1", null, 1 << 20, TimeProvider.System, default);
await ok.DisposeAsync();
}
[Fact]
public async Task PeerListener_WritesNothingToStrangers_NotEvenATlsServerHello()
{
using NodeIdentity probe = NodeIdentity.Generate();
await using var agent = new PeerFixture(_ => probe.PublicKeySpki);
agent.KnockPeers.Add(probe.PublicKeySpki);
using NodeIdentity dialer = NodeIdentity.Generate();
await using var agent = new PeerFixture(_ => dialer.PublicKeySpki);
agent.KnockPeers.Add(dialer.PublicKeySpki);
await agent.Listener.Started.Task;
// 一个像样的 TLS ClientHello 开头、随机数据、什么都不发:都拿不到任何字节(连接被直接关闭)
@@ -495,8 +495,8 @@ public sealed class LinkTests
Assert.Equal(0, read);
}
// 名册里的 Probe 仍然进得来
(_, TlsFrameTransport ok) = await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, probe, "prb_1", null, 1 << 20, TimeProvider.System, default);
// 名册里的 拨号方 仍然进得来
(_, TlsFrameTransport ok) = await PeerConnector.ConnectAsync("127.0.0.1", agent.Listener.Port, agent.PublicKey, dialer, "dlr_1", null, 1 << 20, TimeProvider.System, default);
await ok.DisposeAsync();
}