namespace ZB.MOM.WW.LocalDb.Replication;

/// <summary>
/// Configuration for the bidirectional 2-node replication engine. All durations are wall-clock UTC.
/// </summary>
public sealed class ReplicationOptions
{
    /// <summary>gRPC address of the peer to dial. Required for the initiator role (validated in the sync host).</summary>
    public string PeerAddress { get; set; } = "";

    /// <summary>API key presented to / expected from the peer; null disables key auth.</summary>
    public string? ApiKey { get; set; }

    /// <summary>How often the change pump flushes pending oplog deltas to the peer.</summary>
    public TimeSpan FlushInterval { get; set; } = TimeSpan.FromMilliseconds(250);

    /// <summary>
    /// Secondary, row-count cap on an outbound batch (and the snapshot streamer's DB page size).
    /// <see cref="MaxBatchBytes"/> is the primary cap.
    /// </summary>
    /// <remarks>
    /// Historically this was the ONLY cap, which made it a proxy for a byte budget that consumers
    /// had to tune by hand against their widest row — ScadaBridge pinned it to 16 because a 70 KB
    /// <c>config_json</c> times the 500 default is ~35 MB against a 4 MB gRPC limit. With
    /// <see cref="MaxBatchBytes"/> doing that job directly, this is back to being what its name
    /// says: a bound on how many rows one message may carry.
    /// </remarks>
    public int MaxBatchSize { get; set; } = 500;

    /// <summary>
    /// Primary cap on an outbound batch: the summed serialized size of the entries in one
    /// <c>DeltaBatch</c> / <c>SnapshotBatch</c> message, in bytes. Default 2 MB.
    /// </summary>
    /// <remarks>
    /// <para>
    /// Sized at half the default 4 MB gRPC receive limit, so the message framing, the oneof wrapper
    /// and any per-entry overhead the estimate does not model all fit inside the margin.
    /// </para>
    /// <para>
    /// <b>A single row larger than the budget is still sent, alone.</b> Skipping it would stall the
    /// stream permanently on one oversized row; sending it gives the transport the chance to accept
    /// it (gRPC limits are configurable) and, if it refuses, a loud transport error naming the size
    /// rather than silent non-convergence.
    /// </para>
    /// <para>
    /// <b>Wire compatibility:</b> none required. Batch size is a sender-side choice the protocol
    /// already leaves free — <c>DeltaBatch</c>/<c>SnapshotBatch</c> carry a repeated field with no
    /// declared count — so a node on this version interoperates with a peer on any earlier one in
    /// both directions, with no proto change and no <c>lib_schema_version</c> bump. (ScadaBridge
    /// site pairs stop and start together regardless; this simply does not depend on it.)
    /// </para>
    /// </remarks>
    public int MaxBatchBytes { get; set; } = 2 * 1024 * 1024;

    /// <summary>Backlog ceiling: exceeding it flags a snapshot resync and prunes the oldest oplog rows.</summary>
    public long MaxOplogRows { get; set; } = 1_000_000;

    /// <summary>Age ceiling: an unpruned oplog entry older than this flags a snapshot resync.</summary>
    public TimeSpan MaxOplogAge { get; set; } = TimeSpan.FromDays(7);

    /// <summary>How long deleted-row tombstones are retained before pruning.</summary>
    public TimeSpan TombstoneRetention { get; set; } = TimeSpan.FromDays(7);

    /// <summary>Upper bound on the exponential reconnect backoff.</summary>
    public TimeSpan ReconnectBackoffMax { get; set; } = TimeSpan.FromSeconds(60);

    /// <summary>
    /// How long the initiator's HTTP/2 connection may sit without a keepalive PING before one is
    /// sent. Default 60s.
    /// </summary>
    /// <remarks>
    /// <para>
    /// A sync stream is long-lived and, on a converged pair, almost entirely silent — which is
    /// exactly the shape a half-open TCP connection hides behind. Without pings, a hard crash or a
    /// partition of one node leaves the other holding a stream that will never produce another byte
    /// and never fail either: the initiator sits in a session it believes is healthy, and the
    /// passive node's handler sits inside its single-stream guard, refusing the reconnect that would
    /// heal the pair. Pings turn that into a detected failure on both ends.
    /// </para>
    /// <para>
    /// Sent with <c>KeepAlivePingPolicy.Always</c>, so they flow on an idle connection too — an
    /// active-streams-only policy would not fire in precisely the silent-pair case above. Safe over
    /// h2c: a PING is an HTTP/2 frame, nothing to do with TLS.
    /// </para>
    /// </remarks>
    public TimeSpan KeepAlivePingDelay { get; set; } = TimeSpan.FromSeconds(60);

    /// <summary>
    /// How long the initiator waits for a keepalive PING ack before tearing the connection down.
    /// Default 20s. Detection therefore lands within roughly
    /// <see cref="KeepAlivePingDelay"/> + this.
    /// </summary>
    public TimeSpan KeepAlivePingTimeout { get; set; } = TimeSpan.FromSeconds(20);

    /// <summary>How often the maintenance service enforces the oplog caps and prunes expired tombstones.</summary>
    public TimeSpan MaintenanceInterval { get; set; } = TimeSpan.FromSeconds(60);

    /// <summary>Maximum tolerated HLC drift where a peer's clock runs ahead of ours.</summary>
    public TimeSpan MaxHlcDriftAhead { get; set; } = TimeSpan.FromMinutes(5);

    /// <summary>
    /// When true, entries whose HLC physical time exceeds <see cref="MaxHlcDriftAhead"/> are
    /// dead-lettered individually (the rest of the batch still applies); when false, drifted
    /// entries are applied and a single warning is logged per session.
    /// </summary>
    public bool FailClosedOnDrift { get; set; }
}