Make transactions undroppable

coordinator/cosign/src/delay.rs literally demonstrates how we'd need to rewrite
our handling of transactions with this change. It can be cleaned up a bit but
already identifies ergonomic issues. It also doesn't model passing an &mut txn
to an async function, which would also require using the droppable wrapper
struct.

To locally see this build, run

RUSTFLAGS="-Zpanic_abort_tests -C panic=abort" cargo +nightly build -p serai-cosign --all-targets

To locally see this fail to build, run

cargo build -p serai-cosign --all-targets

While it doesn't say which line causes it fail to build, the only distinction
is panic=unwind.

For more context, please see #578.

.github/workflows/msrv.yml

@@ -173,10 +173,13 @@ jobs:
 
       - name: Run cargo msrv on coordinator
         run: |
-          cargo msrv verify --manifest-path coordinator/tributary/tendermint/Cargo.toml
-          cargo msrv verify --manifest-path coordinator/tributary/Cargo.toml
+          cargo msrv verify --manifest-path coordinator/tributary-sdk/tendermint/Cargo.toml
+          cargo msrv verify --manifest-path coordinator/tributary-sdk/Cargo.toml
           cargo msrv verify --manifest-path coordinator/cosign/Cargo.toml
           cargo msrv verify --manifest-path coordinator/substrate/Cargo.toml
+          cargo msrv verify --manifest-path coordinator/tributary/Cargo.toml
+          cargo msrv verify --manifest-path coordinator/p2p/Cargo.toml
+          cargo msrv verify --manifest-path coordinator/p2p/libp2p/Cargo.toml
           cargo msrv verify --manifest-path coordinator/Cargo.toml
 
   msrv-substrate:

.github/workflows/tests.yml

@@ -60,9 +60,12 @@ jobs:
             -p serai-ethereum-processor \
             -p serai-monero-processor \
             -p tendermint-machine \
-            -p tributary-chain \
+            -p tributary-sdk \
             -p serai-cosign \
             -p serai-coordinator-substrate \
+            -p serai-coordinator-tributary \
+            -p serai-coordinator-p2p \
+            -p serai-coordinator-libp2p-p2p \
             -p serai-coordinator \
             -p serai-orchestrator \
             -p serai-docker-tests

Cargo.lock

@@ -2528,7 +2528,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "33d852cb9b869c2a9b3df2f71a3074817f01e1844f839a144f5fcef059a4eb5d"
 dependencies = [
  "libc",
- "windows-sys 0.52.0",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
@@ -3047,7 +3047,10 @@ version = "2.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cef40d21ae2c515b51041df9ed313ed21e572df340ea58a922a0aefe7e8891a1"
 dependencies = [
+ "fastrand",
  "futures-core",
+ "futures-io",
+ "parking",
  "pin-project-lite",
 ]
 
@@ -3548,7 +3551,7 @@ dependencies = [
  "httpdate",
  "itoa",
  "pin-project-lite",
- "socket2 0.4.10",
+ "socket2 0.5.8",
  "tokio",
  "tower-service",
  "tracing",
@@ -4112,7 +4115,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fc2f4eb4bc735547cfed7c0a4922cbd04a4655978c09b54f1f7b228750664c34"
 dependencies = [
  "cfg-if",
- "windows-targets 0.48.5",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -6907,7 +6910,7 @@ dependencies = [
  "errno",
  "libc",
  "linux-raw-sys",
- "windows-sys 0.52.0",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
@@ -8311,17 +8314,13 @@ dependencies = [
 name = "serai-coordinator"
 version = "0.1.0"
 dependencies = [
- "async-trait",
  "bitvec",
  "blake2",
  "borsh",
  "ciphersuite",
  "env_logger",
- "flexible-transcript",
  "frost-schnorrkel",
- "futures-util",
  "hex",
- "libp2p",
  "log",
  "modular-frost",
  "parity-scale-codec",
@@ -8329,24 +8328,64 @@ dependencies = [
  "schnorr-signatures",
  "schnorrkel",
  "serai-client",
+ "serai-coordinator-libp2p-p2p",
+ "serai-coordinator-p2p",
+ "serai-coordinator-substrate",
+ "serai-coordinator-tributary",
  "serai-cosign",
  "serai-db",
  "serai-env",
  "serai-message-queue",
  "serai-processor-messages",
  "serai-task",
- "sp-application-crypto",
- "sp-runtime",
  "tokio",
- "tributary-chain",
+ "tributary-sdk",
  "zalloc",
  "zeroize",
 ]
 
+[[package]]
+name = "serai-coordinator-libp2p-p2p"
+version = "0.1.0"
+dependencies = [
+ "async-trait",
+ "blake2",
+ "borsh",
+ "futures-util",
+ "hex",
+ "libp2p",
+ "log",
+ "rand_core",
+ "schnorrkel",
+ "serai-client",
+ "serai-coordinator-p2p",
+ "serai-cosign",
+ "serai-task",
+ "tokio",
+ "tributary-sdk",
+ "zeroize",
+]
+
+[[package]]
+name = "serai-coordinator-p2p"
+version = "0.1.0"
+dependencies = [
+ "borsh",
+ "futures-lite",
+ "log",
+ "serai-client",
+ "serai-cosign",
+ "serai-db",
+ "serai-task",
+ "tokio",
+ "tributary-sdk",
+]
+
 [[package]]
 name = "serai-coordinator-substrate"
 version = "0.1.0"
 dependencies = [
+ "bitvec",
  "borsh",
  "futures",
  "log",
@@ -8363,7 +8402,6 @@ dependencies = [
 name = "serai-coordinator-tests"
 version = "0.1.0"
 dependencies = [
- "async-trait",
  "blake2",
  "borsh",
  "ciphersuite",
@@ -8384,6 +8422,27 @@ dependencies = [
  "zeroize",
 ]
 
+[[package]]
+name = "serai-coordinator-tributary"
+version = "0.1.0"
+dependencies = [
+ "blake2",
+ "borsh",
+ "ciphersuite",
+ "log",
+ "parity-scale-codec",
+ "rand_core",
+ "schnorr-signatures",
+ "serai-client",
+ "serai-coordinator-substrate",
+ "serai-cosign",
+ "serai-db",
+ "serai-processor-messages",
+ "serai-task",
+ "tributary-sdk",
+ "zeroize",
+]
+
 [[package]]
 name = "serai-cosign"
 version = "0.1.0"
@@ -8545,7 +8604,6 @@ dependencies = [
 name = "serai-full-stack-tests"
 version = "0.1.0"
 dependencies = [
- "async-trait",
  "bitcoin-serai",
  "curve25519-dalek",
  "dockertest",
@@ -8941,6 +8999,7 @@ dependencies = [
  "hex",
  "parity-scale-codec",
  "serai-coins-primitives",
+ "serai-cosign",
  "serai-in-instructions-primitives",
  "serai-primitives",
  "serai-validator-sets-primitives",
@@ -10491,7 +10550,7 @@ dependencies = [
  "getrandom",
  "once_cell",
  "rustix",
- "windows-sys 0.52.0",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
@@ -10937,7 +10996,7 @@ dependencies = [
 ]
 
 [[package]]
-name = "tributary-chain"
+name = "tributary-sdk"
 version = "0.1.0"
 dependencies = [
  "blake2",
@@ -11715,7 +11774,7 @@ version = "0.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cf221c93e13a30d793f7645a0e7762c55d169dbb0a49671918a2319d289b10bb"
 dependencies = [
- "windows-sys 0.48.0",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]

Cargo.toml

@@ -96,10 +96,13 @@ members = [
   "processor/ethereum",
   "processor/monero",
 
-  "coordinator/tributary/tendermint",
-  "coordinator/tributary",
+  "coordinator/tributary-sdk/tendermint",
+  "coordinator/tributary-sdk",
   "coordinator/cosign",
   "coordinator/substrate",
+  "coordinator/tributary",
+  "coordinator/p2p",
+  "coordinator/p2p/libp2p",
   "coordinator",
 
   "substrate/primitives",

common/db/src/lib.rs

@@ -30,13 +30,53 @@ pub trait Get {
 /// is undefined. The transaction may block, deadlock, panic, overwrite one of the two values
 /// randomly, or any other action, at time of write or at time of commit.
 #[must_use]
-pub trait DbTxn: Send + Get {
+pub trait DbTxn: Sized + Send + Get {
   /// Write a value to this key.
   fn put(&mut self, key: impl AsRef<[u8]>, value: impl AsRef<[u8]>);
   /// Delete the value from this key.
   fn del(&mut self, key: impl AsRef<[u8]>);
   /// Commit this transaction.
   fn commit(self);
+  /// Close this transaction.
+  ///
+  /// This is equivalent to `Drop` on transactions which can be dropped. This is explicit and works
+  /// with transactions which can't be dropped.
+  fn close(self) {
+    drop(self);
+  }
+}
+
+// Credit for the idea goes to https://jack.wrenn.fyi/blog/undroppable
+pub struct Undroppable<T>(Option<T>);
+impl<T> Drop for Undroppable<T> {
+  fn drop(&mut self) {
+    // Use an assertion at compile time to prevent this code from compiling if generated
+    #[allow(clippy::assertions_on_constants)]
+    const {
+      assert!(false, "Undroppable DbTxn was dropped. Ensure all code paths call commit or close");
+    }
+  }
+}
+impl<T: DbTxn> Get for Undroppable<T> {
+  fn get(&self, key: impl AsRef<[u8]>) -> Option<Vec<u8>> {
+    self.0.as_ref().unwrap().get(key)
+  }
+}
+impl<T: DbTxn> DbTxn for Undroppable<T> {
+  fn put(&mut self, key: impl AsRef<[u8]>, value: impl AsRef<[u8]>) {
+    self.0.as_mut().unwrap().put(key, value);
+  }
+  fn del(&mut self, key: impl AsRef<[u8]>) {
+    self.0.as_mut().unwrap().del(key);
+  }
+  fn commit(mut self) {
+    self.0.take().unwrap().commit();
+    let _ = core::mem::ManuallyDrop::new(self);
+  }
+  fn close(mut self) {
+    drop(self.0.take().unwrap());
+    let _ = core::mem::ManuallyDrop::new(self);
+  }
 }
 
 /// A database supporting atomic transaction.
@@ -51,6 +91,10 @@ pub trait Db: 'static + Send + Sync + Clone + Get {
     let dst_len = u8::try_from(item_dst.len()).unwrap();
     [[db_len].as_ref(), db_dst, [dst_len].as_ref(), item_dst, key.as_ref()].concat()
   }
-  /// Open a new transaction.
-  fn txn(&mut self) -> Self::Transaction<'_>;
+  /// Open a new transaction which may be dropped.
+  fn unsafe_txn(&mut self) -> Self::Transaction<'_>;
+  /// Open a new transaction which must be committed or closed.
+  fn txn(&mut self) -> Undroppable<Self::Transaction<'_>> {
+    Undroppable(Some(self.unsafe_txn()))
+  }
 }

common/db/src/mem.rs

@@ -74,7 +74,7 @@ impl Get for MemDb {
 }
 impl Db for MemDb {
   type Transaction<'a> = MemDbTxn<'a>;
-  fn txn(&mut self) -> MemDbTxn<'_> {
+  fn unsafe_txn(&mut self) -> MemDbTxn<'_> {
     MemDbTxn(self, HashMap::new(), HashSet::new())
   }
 }

common/db/src/parity_db.rs

@@ -37,7 +37,7 @@ impl Get for Arc<ParityDb> {
 }
 impl Db for Arc<ParityDb> {
   type Transaction<'a> = Transaction<'a>;
-  fn txn(&mut self) -> Self::Transaction<'_> {
+  fn unsafe_txn(&mut self) -> Self::Transaction<'_> {
     Transaction(self, vec![])
   }
 }

common/db/src/rocks.rs

@@ -39,7 +39,7 @@ impl<T: ThreadMode> Get for Arc<OptimisticTransactionDB<T>> {
 }
 impl<T: Send + ThreadMode + 'static> Db for Arc<OptimisticTransactionDB<T>> {
   type Transaction<'a> = Transaction<'a, T>;
-  fn txn(&mut self) -> Self::Transaction<'_> {
+  fn unsafe_txn(&mut self) -> Self::Transaction<'_> {
     let mut opts = WriteOptions::default();
     opts.set_sync(true);
     Transaction(self.transaction_opt(&opts, &Default::default()), &**self)

common/task/src/lib.rs

@@ -2,10 +2,16 @@
 #![doc = include_str!("../README.md")]
 #![deny(missing_docs)]
 
-use core::{future::Future, time::Duration};
+use core::{
+  fmt::{self, Debug},
+  future::Future,
+  time::Duration,
+};
 
 use tokio::sync::mpsc;
 
+mod type_name;
+
 /// A handle for a task.
 ///
 /// The task will only stop running once all handles for it are dropped.
@@ -45,8 +51,6 @@ impl Task {
 
 impl TaskHandle {
   /// Tell the task to run now (and not whenever its next iteration on a timer is).
-  ///
-  /// Panics if the task has been dropped.
   pub fn run_now(&self) {
     #[allow(clippy::match_same_arms)]
     match self.run_now.try_send(()) {
@@ -54,12 +58,22 @@ impl TaskHandle {
       // NOP on full, as this task will already be ran as soon as possible
       Err(mpsc::error::TrySendError::Full(())) => {}
       Err(mpsc::error::TrySendError::Closed(())) => {
+        // The task should only be closed if all handles are dropped, and this one hasn't been
         panic!("task was unexpectedly closed when calling run_now")
       }
     }
   }
 }
 
+/// An enum which can't be constructed, representing that the task does not error.
+pub enum DoesNotError {}
+impl Debug for DoesNotError {
+  fn fmt(&self, _: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
+    // This type can't be constructed so we'll never have a `&self` to call this fn with
+    unreachable!()
+  }
+}
+
 /// A task to be continually ran.
 pub trait ContinuallyRan: Sized + Send {
   /// The amount of seconds before this task should be polled again.
@@ -69,11 +83,14 @@ pub trait ContinuallyRan: Sized + Send {
   /// Upon error, the amount of time waited will be linearly increased until this limit.
   const MAX_DELAY_BETWEEN_ITERATIONS: u64 = 120;
 
+  /// The error potentially yielded upon running an iteration of this task.
+  type Error: Debug;
+
   /// Run an iteration of the task.
   ///
   /// If this returns `true`, all dependents of the task will immediately have a new iteration ran
   /// (without waiting for whatever timer they were already on).
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>>;
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>>;
 
   /// Continually run the task.
   fn continually_run(
@@ -115,12 +132,20 @@ pub trait ContinuallyRan: Sized + Send {
             }
           }
           Err(e) => {
-            log::warn!("{}", e);
+            // Get the type name
+            let type_name = type_name::strip_type_name(core::any::type_name::<Self>());
+            // Print the error as a warning, prefixed by the task's type
+            log::warn!("{type_name}: {e:?}");
             increase_sleep_before_next_task(&mut current_sleep_before_next_task);
           }
         }
 
         // Don't run the task again for another few seconds UNLESS told to run now
+        /*
+          We could replace tokio::mpsc with async_channel, tokio::time::sleep with
+          patchable_async_sleep::sleep, and tokio::select with futures_lite::future::or
+          It isn't worth the effort when patchable_async_sleep::sleep will still resolve to tokio
+        */
         tokio::select! {
           () = tokio::time::sleep(Duration::from_secs(current_sleep_before_next_task)) => {},
           msg = task.run_now.recv() => {

common/task/src/type_name.rs

@@ -0,0 +1,31 @@
+/// Strip the modules from a type name.
+// This may be of the form `a::b::C`, in which case we only want `C`
+pub(crate) fn strip_type_name(full_type_name: &'static str) -> String {
+  // It also may be `a::b::C<d::e::F>`, in which case, we only attempt to strip `a::b`
+  let mut by_generics = full_type_name.split('<');
+
+  // Strip to just `C`
+  let full_outer_object_name = by_generics.next().unwrap();
+  let mut outer_object_name_parts = full_outer_object_name.split("::");
+  let mut last_part_in_outer_object_name = outer_object_name_parts.next().unwrap();
+  for part in outer_object_name_parts {
+    last_part_in_outer_object_name = part;
+  }
+
+  // Push back on the generic terms
+  let mut type_name = last_part_in_outer_object_name.to_string();
+  for generic in by_generics {
+    type_name.push('<');
+    type_name.push_str(generic);
+  }
+  type_name
+}
+
+#[test]
+fn test_strip_type_name() {
+  assert_eq!(strip_type_name("core::option::Option"), "Option");
+  assert_eq!(
+    strip_type_name("core::option::Option<alloc::string::String>"),
+    "Option<alloc::string::String>"
+  );
+}

coordinator/Cargo.toml

@@ -18,8 +18,6 @@ rustdoc-args = ["--cfg", "docsrs"]
 workspace = true
 
 [dependencies]
-async-trait = { version = "0.1", default-features = false }
-
 zeroize = { version = "^1.5", default-features = false, features = ["std"] }
 bitvec = { version = "1", default-features = false, features = ["std"] }
 rand_core = { version = "0.6", default-features = false, features = ["std"] }
@@ -27,13 +25,12 @@ rand_core = { version = "0.6", default-features = false, features = ["std"] }
 blake2 = { version = "0.10", default-features = false, features = ["std"] }
 schnorrkel = { version = "0.11", default-features = false, features = ["std"] }
 
-transcript = { package = "flexible-transcript", path = "../crypto/transcript", default-features = false, features = ["std", "recommended"] }
 ciphersuite = { path = "../crypto/ciphersuite", default-features = false, features = ["std"] }
 schnorr = { package = "schnorr-signatures", path = "../crypto/schnorr", default-features = false, features = ["std"] }
 frost = { package = "modular-frost", path = "../crypto/frost" }
 frost-schnorrkel = { path = "../crypto/schnorrkel" }
 
-scale = { package = "parity-scale-codec", version = "3", default-features = false, features = ["std", "derive"] }
+scale = { package = "parity-scale-codec", version = "3", default-features = false, features = ["std", "derive", "bit-vec"] }
 
 zalloc = { path = "../common/zalloc" }
 serai-db = { path = "../common/db" }
@@ -42,9 +39,8 @@ serai-task = { path = "../common/task", version = "0.1" }
 
 messages = { package = "serai-processor-messages", path = "../processor/messages" }
 message-queue = { package = "serai-message-queue", path = "../message-queue" }
-tributary = { package = "tributary-chain", path = "./tributary" }
+tributary-sdk = { path = "./tributary-sdk" }
 
-sp-application-crypto = { git = "https://github.com/serai-dex/substrate", default-features = false, features = ["std"] }
 serai-client = { path = "../substrate/client", default-features = false, features = ["serai", "borsh"] }
 
 hex = { version = "0.4", default-features = false, features = ["std"] }
@@ -53,18 +49,15 @@ borsh = { version = "1", default-features = false, features = ["std", "derive",
 log = { version = "0.4", default-features = false, features = ["std"] }
 env_logger = { version = "0.10", default-features = false, features = ["humantime"] }
 
-futures-util = { version = "0.3", default-features = false, features = ["std"] }
-tokio = { version = "1", default-features = false, features = ["rt-multi-thread", "sync", "time", "macros"] }
-libp2p = { version = "0.52", default-features = false, features = ["tokio", "tcp", "noise", "yamux", "request-response", "gossipsub", "macros"] }
+tokio = { version = "1", default-features = false, features = ["time", "sync", "macros", "rt-multi-thread"] }
 
 serai-cosign = { path = "./cosign" }
-
-[dev-dependencies]
-tributary = { package = "tributary-chain", path = "./tributary", features = ["tests"] }
-sp-application-crypto = { git = "https://github.com/serai-dex/substrate", default-features = false, features = ["std"] }
-sp-runtime = { git = "https://github.com/serai-dex/substrate", default-features = false, features = ["std"] }
+serai-coordinator-substrate = { path = "./substrate" }
+serai-coordinator-tributary = { path = "./tributary" }
+serai-coordinator-p2p = { path = "./p2p" }
+serai-coordinator-libp2p-p2p = { path = "./p2p/libp2p" }
 
 [features]
-longer-reattempts = []
+longer-reattempts = ["serai-coordinator-tributary/longer-reattempts"]
 parity-db = ["serai-db/parity-db"]
 rocksdb = ["serai-db/rocksdb"]

coordinator/LICENSE

@@ -1,6 +1,6 @@
 AGPL-3.0-only license
 
-Copyright (c) 2023-2024 Luke Parker
+Copyright (c) 2023-2025 Luke Parker
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU Affero General Public License Version 3 as

coordinator/README.md

@@ -1,19 +1,29 @@
 # Coordinator
 
-- [`tendermint`](/tributary/tendermint) is an implementation of the Tendermint BFT algorithm.
+- [`tendermint`](/tributary/tendermint) is an implementation of the Tendermint
+  BFT algorithm.
 
-- [`tributary`](./tributary) is a micro-blockchain framework. Instead of a producing a blockchain
-  daemon like the Polkadot SDK or Cosmos SDK intend to, `tributary` is solely intended to be an
-  embedded asynchronous task within an application.
+- [`tributary-sdk`](./tributary-sdk) is a micro-blockchain framework. Instead
+  of a producing a blockchain daemon like the Polkadot SDK or Cosmos SDK intend
+  to, `tributary` is solely intended to be an embedded asynchronous task within
+  an application.
 
-  The Serai coordinator spawns a tributary for each validator set it's coordinating. This allows
-  the participating validators to communicate in a byzantine-fault-tolerant manner (relying on
-  Tendermint for consensus).
+  The Serai coordinator spawns a tributary for each validator set it's
+  coordinating. This allows the participating validators to communicate in a
+  byzantine-fault-tolerant manner (relying on Tendermint for consensus).
 
-- [`cosign`](./cosign) contains a library to decide which Substrate blocks should be cosigned and
-  to evaluate cosigns.
+- [`cosign`](./cosign) contains a library to decide which Substrate blocks
+  should be cosigned and to evaluate cosigns.
 
-- [`substrate`](./substrate) contains a library to index the Substrate blockchain and handle its
-  events.
+- [`substrate`](./substrate) contains a library to index the Substrate
+  blockchain and handle its events.
+
+- [`tributary`](./tributary) is our instantiation of the Tributary SDK for the
+  Serai processor. It includes the `Transaction` definition and deferred
+  execution logic.
+
+- [`p2p`](./p2p) is our abstract P2P API to service the Coordinator.
+
+- [`libp2p`](./p2p/libp2p) is our libp2p-backed implementation of the P2P API.
 
 - [`src`](./src) contains the source code for the Coordinator binary itself.

coordinator/cosign/src/delay.rs

@@ -2,7 +2,7 @@ use core::future::Future;
 use std::time::{Duration, SystemTime};
 
 use serai_db::*;
-use serai_task::ContinuallyRan;
+use serai_task::{DoesNotError, ContinuallyRan};
 
 use crate::evaluator::CosignedBlocks;
 
@@ -24,8 +24,19 @@ pub(crate) struct CosignDelayTask<D: Db> {
   pub(crate) db: D,
 }
 
+struct AwaitUndroppable<T: DbTxn>(Option<core::mem::ManuallyDrop<Undroppable<T>>>);
+impl<T: DbTxn> Drop for AwaitUndroppable<T> {
+  fn drop(&mut self) {
+    if let Some(mut txn) = self.0.take() {
+      (unsafe { core::mem::ManuallyDrop::take(&mut txn) }).close();
+    }
+  }
+}
+
 impl<D: Db> ContinuallyRan for CosignDelayTask<D> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = DoesNotError;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       let mut made_progress = false;
       loop {
@@ -33,14 +44,18 @@ impl<D: Db> ContinuallyRan for CosignDelayTask<D> {
 
         // Receive the next block to mark as cosigned
         let Some((block_number, time_evaluated)) = CosignedBlocks::try_recv(&mut txn) else {
+          txn.close();
           break;
         };
+
         // Calculate when we should mark it as valid
         let time_valid =
           SystemTime::UNIX_EPOCH + Duration::from_secs(time_evaluated) + ACKNOWLEDGEMENT_DELAY;
         // Sleep until then
+        let mut txn = AwaitUndroppable(Some(core::mem::ManuallyDrop::new(txn)));
         tokio::time::sleep(SystemTime::now().duration_since(time_valid).unwrap_or(Duration::ZERO))
           .await;
+        let mut txn = core::mem::ManuallyDrop::into_inner(txn.0.take().unwrap());
 
         // Set the cosigned block
         LatestCosignedBlockNumber::set(&mut txn, &block_number);

coordinator/cosign/src/evaluator.rs

@@ -80,12 +80,14 @@ pub(crate) struct CosignEvaluatorTask<D: Db, R: RequestNotableCosigns> {
 }
 
 impl<D: Db, R: RequestNotableCosigns> ContinuallyRan for CosignEvaluatorTask<D, R> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = String;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       let mut known_cosign = None;
       let mut made_progress = false;
       loop {
-        let mut txn = self.db.txn();
+        let mut txn = self.db.unsafe_txn();
         let Some(BlockEventData { block_number, has_events }) = BlockEvents::try_recv(&mut txn)
         else {
           break;

coordinator/cosign/src/intend.rs

@@ -1,5 +1,5 @@
 use core::future::Future;
-use std::collections::HashMap;
+use std::{sync::Arc, collections::HashMap};
 
 use serai_client::{
   primitives::{SeraiAddress, Amount},
@@ -57,18 +57,20 @@ async fn block_has_events_justifying_a_cosign(
 /// A task to determine which blocks we should intend to cosign.
 pub(crate) struct CosignIntendTask<D: Db> {
   pub(crate) db: D,
-  pub(crate) serai: Serai,
+  pub(crate) serai: Arc<Serai>,
 }
 
 impl<D: Db> ContinuallyRan for CosignIntendTask<D> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = String;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       let start_block_number = ScanCosignFrom::get(&self.db).unwrap_or(1);
       let latest_block_number =
         self.serai.latest_finalized_block().await.map_err(|e| format!("{e:?}"))?.number();
 
       for block_number in start_block_number ..= latest_block_number {
-        let mut txn = self.db.txn();
+        let mut txn = self.db.unsafe_txn();
 
         let (block, mut has_events) =
           block_has_events_justifying_a_cosign(&self.serai, block_number)
@@ -78,7 +80,7 @@ impl<D: Db> ContinuallyRan for CosignIntendTask<D> {
         // Check we are indexing a linear chain
         if (block_number > 1) &&
           (<[u8; 32]>::from(block.header.parent_hash) !=
-            SubstrateBlocks::get(&txn, block_number - 1)
+            SubstrateBlockHash::get(&txn, block_number - 1)
               .expect("indexing a block but haven't indexed its parent"))
         {
           Err(format!(
@@ -86,14 +88,15 @@ impl<D: Db> ContinuallyRan for CosignIntendTask<D> {
             block_number - 1
           ))?;
         }
-        SubstrateBlocks::set(&mut txn, block_number, &block.hash());
+        let block_hash = block.hash();
+        SubstrateBlockHash::set(&mut txn, block_number, &block_hash);
 
         let global_session_for_this_block = LatestGlobalSessionIntended::get(&txn);
 
         // If this is notable, it creates a new global session, which we index into the database
         // now
         if has_events == HasEvents::Notable {
-          let serai = self.serai.as_of(block.hash());
+          let serai = self.serai.as_of(block_hash);
           let sets_and_keys = cosigning_sets(&serai).await?;
           let global_session =
             GlobalSession::id(sets_and_keys.iter().map(|(set, _key)| *set).collect());
@@ -159,7 +162,7 @@ impl<D: Db> ContinuallyRan for CosignIntendTask<D> {
                 &CosignIntent {
                   global_session: global_session_for_this_block,
                   block_number,
-                  block_hash: block.hash(),
+                  block_hash,
                   notable: has_events == HasEvents::Notable,
                 },
               );

coordinator/cosign/src/lib.rs

@@ -3,7 +3,7 @@
 #![deny(missing_docs)]
 
 use core::{fmt::Debug, future::Future};
-use std::collections::HashMap;
+use std::{sync::Arc, collections::HashMap};
 
 use blake2::{Digest, Blake2s256};
 
@@ -82,13 +82,13 @@ enum HasEvents {
 #[derive(Clone, Copy, PartialEq, Eq, Debug, BorshSerialize, BorshDeserialize)]
 pub struct CosignIntent {
   /// The global session this cosign is being performed under.
-  global_session: [u8; 32],
+  pub global_session: [u8; 32],
   /// The number of the block to cosign.
-  block_number: u64,
+  pub block_number: u64,
   /// The hash of the block to cosign.
-  block_hash: [u8; 32],
+  pub block_hash: [u8; 32],
   /// If this cosign must be handled before further cosigns are.
-  notable: bool,
+  pub notable: bool,
 }
 
 /// A cosign.
@@ -127,7 +127,7 @@ create_db! {
     // The following are populated by the intend task and used throughout the library
 
     // An index of Substrate blocks
-    SubstrateBlocks: (block_number: u64) -> [u8; 32],
+    SubstrateBlockHash: (block_number: u64) -> [u8; 32],
     // A mapping from a global session's ID to its relevant information.
     GlobalSessions: (global_session: [u8; 32]) -> GlobalSession,
     // The last block to be cosigned by a global session.
@@ -228,6 +228,43 @@ pub trait RequestNotableCosigns: 'static + Send {
 #[derive(Debug)]
 pub struct Faulted;
 
+/// An error incurred while intaking a cosign.
+#[derive(Debug)]
+pub enum IntakeCosignError {
+  /// Cosign is for a not-yet-indexed block
+  NotYetIndexedBlock,
+  /// A later cosign for this cosigner has already been handled
+  StaleCosign,
+  /// The cosign's global session isn't recognized
+  UnrecognizedGlobalSession,
+  /// The cosign is for a block before its global session starts
+  BeforeGlobalSessionStart,
+  /// The cosign is for a block after its global session ends
+  AfterGlobalSessionEnd,
+  /// The cosign's signing network wasn't a participant in this global session
+  NonParticipatingNetwork,
+  /// The cosign had an invalid signature
+  InvalidSignature,
+  /// The cosign is for a global session which has yet to have its declaration block cosigned
+  FutureGlobalSession,
+}
+
+impl IntakeCosignError {
+  /// If this error is temporal to the local view
+  pub fn temporal(&self) -> bool {
+    match self {
+      IntakeCosignError::NotYetIndexedBlock |
+      IntakeCosignError::StaleCosign |
+      IntakeCosignError::UnrecognizedGlobalSession |
+      IntakeCosignError::FutureGlobalSession => true,
+      IntakeCosignError::BeforeGlobalSessionStart |
+      IntakeCosignError::AfterGlobalSessionEnd |
+      IntakeCosignError::NonParticipatingNetwork |
+      IntakeCosignError::InvalidSignature => false,
+    }
+  }
+}
+
 /// The interface to manage cosigning with.
 pub struct Cosigning<D: Db> {
   db: D,
@@ -239,7 +276,7 @@ impl<D: Db> Cosigning<D> {
   /// only used once at any given time.
   pub fn spawn<R: RequestNotableCosigns>(
     db: D,
-    serai: Serai,
+    serai: Arc<Serai>,
     request: R,
     tasks_to_run_upon_cosigning: Vec<TaskHandle>,
   ) -> Self {
@@ -270,14 +307,14 @@ impl<D: Db> Cosigning<D> {
     Ok(LatestCosignedBlockNumber::get(getter).unwrap_or(0))
   }
 
-  /// Fetch an cosigned Substrate block by its block number.
+  /// Fetch a cosigned Substrate block's hash by its block number.
   pub fn cosigned_block(getter: &impl Get, block_number: u64) -> Result<Option<[u8; 32]>, Faulted> {
     if block_number > Self::latest_cosigned_block_number(getter)? {
       return Ok(None);
     }
 
     Ok(Some(
-      SubstrateBlocks::get(getter, block_number).expect("cosigned block but didn't index it"),
+      SubstrateBlockHash::get(getter, block_number).expect("cosigned block but didn't index it"),
     ))
   }
 
@@ -326,27 +363,16 @@ impl<D: Db> Cosigning<D> {
     }
   }
 
-  /// Intake a cosign from the Serai network.
-  ///
-  /// - Returns Err(_) if there was an error trying to validate the cosign and it should be retired
-  ///   later.
-  /// - Returns Ok(true) if the cosign was successfully handled or could not be handled at this
-  ///   time.
-  /// - Returns Ok(false) if the cosign was invalid.
-  //
-  // We collapse a cosign which shouldn't be handled yet into a valid cosign (`Ok(true)`) as we
-  // assume we'll either explicitly request it if we need it or we'll naturally see it (or a later,
-  // more relevant, cosign) again.
+  /// Intake a cosign.
   //
   // Takes `&mut self` as this should only be called once at any given moment.
-  // TODO: Don't overload bool here
-  pub fn intake_cosign(&mut self, signed_cosign: &SignedCosign) -> Result<bool, String> {
+  pub fn intake_cosign(&mut self, signed_cosign: &SignedCosign) -> Result<(), IntakeCosignError> {
     let cosign = &signed_cosign.cosign;
     let network = cosign.cosigner;
 
     // Check our indexed blockchain includes a block with this block number
-    let Some(our_block_hash) = SubstrateBlocks::get(&self.db, cosign.block_number) else {
-      return Ok(true);
+    let Some(our_block_hash) = SubstrateBlockHash::get(&self.db, cosign.block_number) else {
+      Err(IntakeCosignError::NotYetIndexedBlock)?
     };
     let faulty = cosign.block_hash != our_block_hash;
 
@@ -356,20 +382,19 @@ impl<D: Db> Cosigning<D> {
         NetworksLatestCosignedBlock::get(&self.db, cosign.global_session, network)
       {
         if existing.cosign.block_number >= cosign.block_number {
-          return Ok(true);
+          Err(IntakeCosignError::StaleCosign)?;
         }
       }
     }
 
     let Some(global_session) = GlobalSessions::get(&self.db, cosign.global_session) else {
-      // Unrecognized global session
-      return Ok(true);
+      Err(IntakeCosignError::UnrecognizedGlobalSession)?
     };
 
     // Check the cosigned block number is in range to the global session
     if cosign.block_number < global_session.start_block_number {
       // Cosign is for a block predating the global session
-      return Ok(false);
+      Err(IntakeCosignError::BeforeGlobalSessionStart)?;
     }
     if !faulty {
       // This prevents a malicious validator set, on the same chain, from producing a cosign after
@@ -377,7 +402,7 @@ impl<D: Db> Cosigning<D> {
       if let Some(last_block) = GlobalSessionsLastBlock::get(&self.db, cosign.global_session) {
         if cosign.block_number > last_block {
           // Cosign is for a block after the last block this global session should have signed
-          return Ok(false);
+          Err(IntakeCosignError::AfterGlobalSessionEnd)?;
         }
       }
     }
@@ -386,20 +411,20 @@ impl<D: Db> Cosigning<D> {
     {
       let key = Public::from({
         let Some(key) = global_session.keys.get(&network) else {
-          return Ok(false);
+          Err(IntakeCosignError::NonParticipatingNetwork)?
         };
         *key
       });
 
       if !signed_cosign.verify_signature(key) {
-        return Ok(false);
+        Err(IntakeCosignError::InvalidSignature)?;
       }
     }
 
     // Since we verified this cosign's signature, and have a chain sufficiently long, handle the
     // cosign
 
-    let mut txn = self.db.txn();
+    let mut txn = self.db.unsafe_txn();
 
     if !faulty {
       // If this is for a future global session, we don't acknowledge this cosign at this time
@@ -408,7 +433,7 @@ impl<D: Db> Cosigning<D> {
       // block declaring it was cosigned
       if (global_session.start_block_number - 1) > latest_cosigned_block_number {
         drop(txn);
-        return Ok(true);
+        return Err(IntakeCosignError::FutureGlobalSession);
       }
 
       // This is safe as it's in-range and newer, as prior checked since it isn't faulty
@@ -422,9 +447,10 @@ impl<D: Db> Cosigning<D> {
 
         let mut weight_cosigned = 0;
         for fault in &faults {
-          let Some(stake) = global_session.stakes.get(&fault.cosign.cosigner) else {
-            Err("cosigner with recognized key didn't have a stake entry saved".to_string())?
-          };
+          let stake = global_session
+            .stakes
+            .get(&fault.cosign.cosigner)
+            .expect("cosigner with recognized key didn't have a stake entry saved");
           weight_cosigned += stake;
         }
 
@@ -436,7 +462,7 @@ impl<D: Db> Cosigning<D> {
     }
 
     txn.commit();
-    Ok(true)
+    Ok(())
   }
 
   /// Receive intended cosigns to produce for this ValidatorSet.
@@ -454,3 +480,30 @@ impl<D: Db> Cosigning<D> {
     res
   }
 }
+
+mod tests {
+  use super::*;
+
+  struct RNC;
+  impl RequestNotableCosigns for RNC {
+    /// The error type which may be encountered when requesting notable cosigns.
+    type Error = ();
+
+    /// Request the notable cosigns for this global session.
+    fn request_notable_cosigns(
+      &self,
+      global_session: [u8; 32],
+    ) -> impl Send + Future<Output = Result<(), Self::Error>> {
+      async move { Ok(()) }
+    }
+  }
+  #[tokio::test]
+  async fn test() {
+    let db: serai_db::MemDb = serai_db::MemDb::new();
+    let serai = unsafe { core::mem::transmute(0u64) };
+    let request = RNC;
+    let tasks = vec![];
+    let _ = Cosigning::spawn(db, serai, request, tasks);
+    core::future::pending().await
+  }
+}

coordinator/p2p/Cargo.toml

@@ -0,0 +1,33 @@
+[package]
+name = "serai-coordinator-p2p"
+version = "0.1.0"
+description = "Serai coordinator's P2P abstraction"
+license = "AGPL-3.0-only"
+repository = "https://github.com/serai-dex/serai/tree/develop/coordinator/p2p"
+authors = ["Luke Parker <lukeparker5132@gmail.com>"]
+keywords = []
+edition = "2021"
+publish = false
+rust-version = "1.81"
+
+[package.metadata.docs.rs]
+all-features = true
+rustdoc-args = ["--cfg", "docsrs"]
+
+[lints]
+workspace = true
+
+[dependencies]
+borsh = { version = "1", default-features = false, features = ["std", "derive", "de_strict_order"] }
+
+serai-db = { path = "../../common/db", version = "0.1" }
+
+serai-client = { path = "../../substrate/client", default-features = false, features = ["serai", "borsh"] }
+serai-cosign = { path = "../cosign" }
+tributary-sdk = { path = "../tributary-sdk" }
+
+futures-lite = { version = "2", default-features = false, features = ["std"] }
+tokio = { version = "1", default-features = false, features = ["sync", "macros"] }
+
+log = { version = "0.4", default-features = false, features = ["std"] }
+serai-task = { path = "../../common/task", version = "0.1" }

coordinator/p2p/LICENSE

@@ -0,0 +1,15 @@
+AGPL-3.0-only license
+
+Copyright (c) 2023-2025 Luke Parker
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU Affero General Public License Version 3 as
+published by the Free Software Foundation.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program. If not, see <http://www.gnu.org/licenses/>.

coordinator/p2p/README.md

@@ -0,0 +1,3 @@
+# Serai Coordinator P2P
+
+The P2P abstraction used by Serai's coordinator, and tasks over it.

coordinator/p2p/libp2p/Cargo.toml

@@ -0,0 +1,42 @@
+[package]
+name = "serai-coordinator-libp2p-p2p"
+version = "0.1.0"
+description = "Serai coordinator's libp2p-based P2P backend"
+license = "AGPL-3.0-only"
+repository = "https://github.com/serai-dex/serai/tree/develop/coordinator/p2p/libp2p"
+authors = ["Luke Parker <lukeparker5132@gmail.com>"]
+keywords = []
+edition = "2021"
+publish = false
+rust-version = "1.81"
+
+[package.metadata.docs.rs]
+all-features = true
+rustdoc-args = ["--cfg", "docsrs"]
+
+[lints]
+workspace = true
+
+[dependencies]
+async-trait = { version = "0.1", default-features = false }
+
+rand_core = { version = "0.6", default-features = false, features = ["std"] }
+
+zeroize = { version = "^1.5", default-features = false, features = ["std"] }
+blake2 = { version = "0.10", default-features = false, features = ["std"] }
+schnorrkel = { version = "0.11", default-features = false, features = ["std"] }
+
+hex = { version = "0.4", default-features = false, features = ["std"] }
+borsh = { version = "1", default-features = false, features = ["std", "derive", "de_strict_order"] }
+
+serai-client = { path = "../../../substrate/client", default-features = false, features = ["serai", "borsh"] }
+serai-cosign = { path = "../../cosign" }
+tributary-sdk = { path = "../../tributary-sdk" }
+
+futures-util = { version = "0.3", default-features = false, features = ["std"] }
+tokio = { version = "1", default-features = false, features = ["sync"] }
+libp2p = { version = "0.52", default-features = false, features = ["tokio", "tcp", "noise", "yamux", "ping", "request-response", "gossipsub", "macros"] }
+
+log = { version = "0.4", default-features = false, features = ["std"] }
+serai-task = { path = "../../../common/task", version = "0.1" }
+serai-coordinator-p2p = { path = "../" }

coordinator/p2p/libp2p/LICENSE

@@ -0,0 +1,15 @@
+AGPL-3.0-only license
+
+Copyright (c) 2023-2025 Luke Parker
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU Affero General Public License Version 3 as
+published by the Free Software Foundation.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program. If not, see <http://www.gnu.org/licenses/>.

coordinator/p2p/libp2p/README.md

@@ -0,0 +1,14 @@
+# Serai Coordinator libp2p P2P
+
+A libp2p-backed P2P instantiation for Serai's coordinator.
+
+The libp2p swarm is limited to validators from the Serai network. The swarm
+does not maintain any of its own peer finding/routing infrastructure, instead
+relying on the Serai network's connection information to dial peers. This does
+limit the listening peers to only the peers immediately reachable via the same
+IP address (despite the two distinct services), not hidden behind a NAT, yet is
+also quite simple and gives full control of who to connect to to us.
+
+Peers are decided via the internal `DialTask` which aims to maintain a target
+amount of peers for each external network. This ensures cosigns are able to
+propagate across the external networks which sign them.

coordinator/p2p/libp2p/src/authenticate.rs

@@ -1,5 +1,5 @@
 use core::{pin::Pin, future::Future};
-use std::{sync::Arc, io};
+use std::io;
 
 use zeroize::Zeroizing;
 use rand_core::{RngCore, OsRng};
@@ -9,8 +9,6 @@ use schnorrkel::{Keypair, PublicKey, Signature};
 
 use serai_client::primitives::PublicKey as Public;
 
-use tokio::sync::RwLock;
-
 use futures_util::{AsyncRead, AsyncReadExt, AsyncWrite, AsyncWriteExt};
 use libp2p::{
   core::UpgradeInfo,
@@ -19,13 +17,12 @@ use libp2p::{
   noise,
 };
 
-use crate::p2p::libp2p::{validators::Validators, peer_id_from_public};
+use crate::peer_id_from_public;
 
 const PROTOCOL: &str = "/serai/coordinator/validators";
 
 #[derive(Clone)]
 pub(crate) struct OnlyValidators {
-  pub(crate) validators: Arc<RwLock<Validators>>,
   pub(crate) serai_key: Zeroizing<Keypair>,
   pub(crate) noise_keypair: identity::Keypair,
 }
@@ -108,12 +105,7 @@ impl OnlyValidators {
       .verify_simple(PROTOCOL.as_bytes(), &msg, &sig)
       .map_err(|_| io::Error::other("invalid signature"))?;
 
-    let peer_id = peer_id_from_public(Public::from_raw(public_key.to_bytes()));
-    if !self.validators.read().await.contains(&peer_id) {
-      Err(io::Error::other("peer which tried to connect isn't a known active validator"))?;
-    }
-
-    Ok(peer_id)
+    Ok(peer_id_from_public(Public::from_raw(public_key.to_bytes())))
   }
 }
 

coordinator/p2p/libp2p/src/dial.rs

@@ -1,11 +1,11 @@
 use core::future::Future;
-use std::collections::HashSet;
+use std::{sync::Arc, collections::HashSet};
 
 use rand_core::{RngCore, OsRng};
 
 use tokio::sync::mpsc;
 
-use serai_client::Serai;
+use serai_client::{SeraiError, Serai};
 
 use libp2p::{
   core::multiaddr::{Protocol, Multiaddr},
@@ -14,7 +14,7 @@ use libp2p::{
 
 use serai_task::ContinuallyRan;
 
-use crate::p2p::libp2p::{PORT, Peers, validators::Validators};
+use crate::{PORT, Peers, validators::Validators};
 
 const TARGET_PEERS_PER_NETWORK: usize = 5;
 /*
@@ -29,15 +29,19 @@ const TARGET_PEERS_PER_NETWORK: usize = 5;
 // TODO const TARGET_DIALED_PEERS_PER_NETWORK: usize = 3;
 
 pub(crate) struct DialTask {
-  serai: Serai,
+  serai: Arc<Serai>,
   validators: Validators,
   peers: Peers,
   to_dial: mpsc::UnboundedSender<DialOpts>,
 }
 
 impl DialTask {
-  pub(crate) fn new(serai: Serai, peers: Peers, to_dial: mpsc::UnboundedSender<DialOpts>) -> Self {
-    DialTask { serai: serai.clone(), validators: Validators::new(serai), peers, to_dial }
+  pub(crate) fn new(
+    serai: Arc<Serai>,
+    peers: Peers,
+    to_dial: mpsc::UnboundedSender<DialOpts>,
+  ) -> Self {
+    DialTask { serai: serai.clone(), validators: Validators::new(serai).0, peers, to_dial }
   }
 }
 
@@ -46,7 +50,9 @@ impl ContinuallyRan for DialTask {
   const DELAY_BETWEEN_ITERATIONS: u64 = 5 * 60;
   const MAX_DELAY_BETWEEN_ITERATIONS: u64 = 10 * 60;
 
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = SeraiError;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       self.validators.update().await?;
 
@@ -79,8 +85,7 @@ impl ContinuallyRan for DialTask {
               .unwrap_or(0)
               .saturating_sub(1))
         {
-          let mut potential_peers =
-            self.serai.p2p_validators(network).await.map_err(|e| format!("{e:?}"))?;
+          let mut potential_peers = self.serai.p2p_validators(network).await?;
           for _ in 0 .. (TARGET_PEERS_PER_NETWORK - peer_count) {
             if potential_peers.is_empty() {
               break;

coordinator/p2p/libp2p/src/gossip.rs

@@ -2,41 +2,37 @@ use core::time::Duration;
 
 use blake2::{Digest, Blake2s256};
 
-use scale::Encode;
 use borsh::{BorshSerialize, BorshDeserialize};
-use serai_client::validator_sets::primitives::ValidatorSet;
 
 use libp2p::gossipsub::{
-  TopicHash, IdentTopic, MessageId, MessageAuthenticity, ValidationMode, ConfigBuilder,
-  IdentityTransform, AllowAllSubscriptionFilter, Behaviour,
+  IdentTopic, MessageId, MessageAuthenticity, ValidationMode, ConfigBuilder, IdentityTransform,
+  AllowAllSubscriptionFilter, Behaviour,
 };
 pub use libp2p::gossipsub::Event;
 
 use serai_cosign::SignedCosign;
 
 // Block size limit + 16 KB of space for signatures/metadata
-pub(crate) const MAX_LIBP2P_GOSSIP_MESSAGE_SIZE: usize = tributary::BLOCK_SIZE_LIMIT + 16384;
-
-const KEEP_ALIVE_INTERVAL: Duration = Duration::from_secs(80);
+pub(crate) const MAX_LIBP2P_GOSSIP_MESSAGE_SIZE: usize = tributary_sdk::BLOCK_SIZE_LIMIT + 16384;
 
 const LIBP2P_PROTOCOL: &str = "/serai/coordinator/gossip/1.0.0";
 const BASE_TOPIC: &str = "/";
 
-fn topic_for_set(set: ValidatorSet) -> IdentTopic {
-  IdentTopic::new(format!("/set/{}", hex::encode(set.encode())))
+fn topic_for_tributary(tributary: [u8; 32]) -> IdentTopic {
+  IdentTopic::new(format!("/tributary/{}", hex::encode(tributary)))
 }
 
 #[derive(Clone, BorshSerialize, BorshDeserialize)]
 pub(crate) enum Message {
-  Tributary { set: ValidatorSet, message: Vec<u8> },
+  Tributary { tributary: [u8; 32], message: Vec<u8> },
   Cosign(SignedCosign),
 }
 
 impl Message {
-  pub(crate) fn topic(&self) -> TopicHash {
+  pub(crate) fn topic(&self) -> IdentTopic {
     match self {
-      Message::Tributary { set, .. } => topic_for_set(*set).hash(),
-      Message::Cosign(_) => IdentTopic::new(BASE_TOPIC).hash(),
+      Message::Tributary { tributary, .. } => topic_for_tributary(*tributary),
+      Message::Cosign(_) => IdentTopic::new(BASE_TOPIC),
     }
   }
 }
@@ -46,9 +42,10 @@ pub(crate) type Behavior = Behaviour<IdentityTransform, AllowAllSubscriptionFilt
 pub(crate) fn new_behavior() -> Behavior {
   // The latency used by the Tendermint protocol, used here as the gossip epoch duration
   // libp2p-rs defaults to 1 second, whereas ours will be ~2
-  let heartbeat_interval = tributary::tendermint::LATENCY_TIME;
+  let heartbeat_interval = tributary_sdk::tendermint::LATENCY_TIME;
   // The amount of heartbeats which will occur within a single Tributary block
-  let heartbeats_per_block = tributary::tendermint::TARGET_BLOCK_TIME.div_ceil(heartbeat_interval);
+  let heartbeats_per_block =
+    tributary_sdk::tendermint::TARGET_BLOCK_TIME.div_ceil(heartbeat_interval);
   // libp2p-rs defaults to 5, whereas ours will be ~8
   let heartbeats_to_keep = 2 * heartbeats_per_block;
   // libp2p-rs defaults to 3 whereas ours will be ~4
@@ -60,7 +57,6 @@ pub(crate) fn new_behavior() -> Behavior {
     .history_gossip(usize::try_from(heartbeats_to_gossip).unwrap())
     .heartbeat_interval(Duration::from_millis(heartbeat_interval.into()))
     .max_transmit_size(MAX_LIBP2P_GOSSIP_MESSAGE_SIZE)
-    .idle_timeout(KEEP_ALIVE_INTERVAL + Duration::from_secs(5))
     .duplicate_cache_time(Duration::from_millis((heartbeats_to_keep * heartbeat_interval).into()))
     .validation_mode(ValidationMode::Anonymous)
     // Uses a content based message ID to avoid duplicates as much as possible

coordinator/p2p/libp2p/src/lib.rs

@@ -0,0 +1,433 @@
+#![cfg_attr(docsrs, feature(doc_auto_cfg))]
+#![doc = include_str!("../README.md")]
+#![deny(missing_docs)]
+
+use core::{future::Future, time::Duration};
+use std::{
+  sync::Arc,
+  collections::{HashSet, HashMap},
+};
+
+use rand_core::{RngCore, OsRng};
+
+use zeroize::Zeroizing;
+use schnorrkel::Keypair;
+
+use serai_client::{
+  primitives::{NetworkId, PublicKey},
+  validator_sets::primitives::ValidatorSet,
+  Serai,
+};
+
+use tokio::sync::{mpsc, oneshot, Mutex, RwLock};
+
+use serai_task::{Task, ContinuallyRan};
+
+use serai_cosign::SignedCosign;
+
+use libp2p::{
+  multihash::Multihash,
+  identity::{self, PeerId},
+  tcp::Config as TcpConfig,
+  yamux, allow_block_list,
+  connection_limits::{self, ConnectionLimits},
+  swarm::NetworkBehaviour,
+  SwarmBuilder,
+};
+
+use serai_coordinator_p2p::{Heartbeat, TributaryBlockWithCommit};
+
+/// A struct to sync the validators from the Serai node in order to keep track of them.
+mod validators;
+use validators::UpdateValidatorsTask;
+
+/// The authentication protocol upgrade to limit the P2P network to active validators.
+mod authenticate;
+use authenticate::OnlyValidators;
+
+/// The ping behavior, used to ensure connection latency is below the limit
+mod ping;
+
+/// The request-response messages and behavior
+mod reqres;
+use reqres::{RequestId, Request, Response};
+
+/// The gossip messages and behavior
+mod gossip;
+use gossip::Message;
+
+/// The swarm task, running it and dispatching to/from it
+mod swarm;
+use swarm::SwarmTask;
+
+/// The dial task, to find new peers to connect to
+mod dial;
+use dial::DialTask;
+
+const PORT: u16 = 30563; // 5132 ^ (('c' << 8) | 'o')
+
+// usize::max, manually implemented, as max isn't a const fn
+const MAX_LIBP2P_MESSAGE_SIZE: usize =
+  if gossip::MAX_LIBP2P_GOSSIP_MESSAGE_SIZE > reqres::MAX_LIBP2P_REQRES_MESSAGE_SIZE {
+    gossip::MAX_LIBP2P_GOSSIP_MESSAGE_SIZE
+  } else {
+    reqres::MAX_LIBP2P_REQRES_MESSAGE_SIZE
+  };
+
+fn peer_id_from_public(public: PublicKey) -> PeerId {
+  // 0 represents the identity Multihash, that no hash was performed
+  // It's an internal constant so we can't refer to the constant inside libp2p
+  PeerId::from_multihash(Multihash::wrap(0, &public.0).unwrap()).unwrap()
+}
+
+/// The representation of a peer.
+pub struct Peer<'a> {
+  outbound_requests: &'a mpsc::UnboundedSender<(PeerId, Request, oneshot::Sender<Response>)>,
+  id: PeerId,
+}
+impl serai_coordinator_p2p::Peer<'_> for Peer<'_> {
+  fn send_heartbeat(
+    &self,
+    heartbeat: Heartbeat,
+  ) -> impl Send + Future<Output = Option<Vec<TributaryBlockWithCommit>>> {
+    async move {
+      const HEARTBEAT_TIMEOUT: Duration = Duration::from_secs(5);
+
+      let request = Request::Heartbeat(heartbeat);
+      let (sender, receiver) = oneshot::channel();
+      self
+        .outbound_requests
+        .send((self.id, request, sender))
+        .expect("outbound requests recv channel was dropped?");
+      if let Ok(Ok(Response::Blocks(blocks))) =
+        tokio::time::timeout(HEARTBEAT_TIMEOUT, receiver).await
+      {
+        Some(blocks)
+      } else {
+        None
+      }
+    }
+  }
+}
+
+#[derive(Clone)]
+struct Peers {
+  peers: Arc<RwLock<HashMap<NetworkId, HashSet<PeerId>>>>,
+}
+
+// Consider adding identify/kad/autonat/rendevous/(relay + dcutr). While we currently use the Serai
+// network for peers, we could use it solely for bootstrapping/as a fallback.
+#[derive(NetworkBehaviour)]
+struct Behavior {
+  // Used to only allow Serai validators as peers
+  allow_list: allow_block_list::Behaviour<allow_block_list::AllowedPeers>,
+  // Used to limit each peer to a single connection
+  connection_limits: connection_limits::Behaviour,
+  // Used to ensure connection latency is within tolerances
+  ping: ping::Behavior,
+  // Used to request data from specific peers
+  reqres: reqres::Behavior,
+  // Used to broadcast messages to all other peers subscribed to a topic
+  gossip: gossip::Behavior,
+}
+
+#[allow(clippy::type_complexity)]
+struct Libp2pInner {
+  peers: Peers,
+
+  gossip: mpsc::UnboundedSender<Message>,
+  outbound_requests: mpsc::UnboundedSender<(PeerId, Request, oneshot::Sender<Response>)>,
+
+  tributary_gossip: Mutex<mpsc::UnboundedReceiver<([u8; 32], Vec<u8>)>>,
+
+  signed_cosigns: Mutex<mpsc::UnboundedReceiver<SignedCosign>>,
+  signed_cosigns_send: mpsc::UnboundedSender<SignedCosign>,
+
+  heartbeat_requests: Mutex<mpsc::UnboundedReceiver<(RequestId, ValidatorSet, [u8; 32])>>,
+  notable_cosign_requests: Mutex<mpsc::UnboundedReceiver<(RequestId, [u8; 32])>>,
+  inbound_request_responses: mpsc::UnboundedSender<(RequestId, Response)>,
+}
+
+/// The libp2p-backed P2P implementation.
+///
+/// The P2p trait implementation does not support backpressure and is expected to be fully
+/// utilized. Failure to poll the entire API will cause unbounded memory growth.
+#[derive(Clone)]
+pub struct Libp2p(Arc<Libp2pInner>);
+
+impl Libp2p {
+  /// Create a new libp2p-backed P2P instance.
+  ///
+  /// This will spawn all of the internal tasks necessary for functioning.
+  pub fn new(serai_key: &Zeroizing<Keypair>, serai: Arc<Serai>) -> Libp2p {
+    // Define the object we track peers with
+    let peers = Peers { peers: Arc::new(RwLock::new(HashMap::new())) };
+
+    // Define the dial task
+    let (dial_task_def, dial_task) = Task::new();
+    let (to_dial_send, to_dial_recv) = mpsc::unbounded_channel();
+    tokio::spawn(
+      DialTask::new(serai.clone(), peers.clone(), to_dial_send)
+        .continually_run(dial_task_def, vec![]),
+    );
+
+    let swarm = {
+      let new_only_validators = |noise_keypair: &identity::Keypair| -> Result<_, ()> {
+        Ok(OnlyValidators { serai_key: serai_key.clone(), noise_keypair: noise_keypair.clone() })
+      };
+
+      let new_yamux = || {
+        let mut config = yamux::Config::default();
+        // 1 MiB default + max message size
+        config.set_max_buffer_size((1024 * 1024) + MAX_LIBP2P_MESSAGE_SIZE);
+        // 256 KiB default + max message size
+        config
+          .set_receive_window_size(((256 * 1024) + MAX_LIBP2P_MESSAGE_SIZE).try_into().unwrap());
+        config
+      };
+
+      let mut swarm = SwarmBuilder::with_existing_identity(identity::Keypair::generate_ed25519())
+        .with_tokio()
+        .with_tcp(TcpConfig::default().nodelay(true), new_only_validators, new_yamux)
+        .unwrap()
+        .with_behaviour(|_| Behavior {
+          allow_list: allow_block_list::Behaviour::default(),
+          // Limit each per to a single connection
+          connection_limits: connection_limits::Behaviour::new(
+            ConnectionLimits::default().with_max_established_per_peer(Some(1)),
+          ),
+          ping: ping::new_behavior(),
+          reqres: reqres::new_behavior(),
+          gossip: gossip::new_behavior(),
+        })
+        .unwrap()
+        .with_swarm_config(|config| {
+          config
+            .with_idle_connection_timeout(ping::INTERVAL + ping::TIMEOUT + Duration::from_secs(5))
+        })
+        .build();
+      swarm.listen_on(format!("/ip4/0.0.0.0/tcp/{PORT}").parse().unwrap()).unwrap();
+      swarm.listen_on(format!("/ip6/::/tcp/{PORT}").parse().unwrap()).unwrap();
+      swarm
+    };
+
+    let (swarm_validators, validator_changes) = UpdateValidatorsTask::spawn(serai);
+
+    let (gossip_send, gossip_recv) = mpsc::unbounded_channel();
+    let (signed_cosigns_send, signed_cosigns_recv) = mpsc::unbounded_channel();
+    let (tributary_gossip_send, tributary_gossip_recv) = mpsc::unbounded_channel();
+
+    let (outbound_requests_send, outbound_requests_recv) = mpsc::unbounded_channel();
+
+    let (heartbeat_requests_send, heartbeat_requests_recv) = mpsc::unbounded_channel();
+    let (notable_cosign_requests_send, notable_cosign_requests_recv) = mpsc::unbounded_channel();
+    let (inbound_request_responses_send, inbound_request_responses_recv) =
+      mpsc::unbounded_channel();
+
+    // Create the swarm task
+    SwarmTask::spawn(
+      dial_task,
+      to_dial_recv,
+      swarm_validators,
+      validator_changes,
+      peers.clone(),
+      swarm,
+      gossip_recv,
+      signed_cosigns_send.clone(),
+      tributary_gossip_send,
+      outbound_requests_recv,
+      heartbeat_requests_send,
+      notable_cosign_requests_send,
+      inbound_request_responses_recv,
+    );
+
+    Libp2p(Arc::new(Libp2pInner {
+      peers,
+
+      gossip: gossip_send,
+      outbound_requests: outbound_requests_send,
+
+      tributary_gossip: Mutex::new(tributary_gossip_recv),
+
+      signed_cosigns: Mutex::new(signed_cosigns_recv),
+      signed_cosigns_send,
+
+      heartbeat_requests: Mutex::new(heartbeat_requests_recv),
+      notable_cosign_requests: Mutex::new(notable_cosign_requests_recv),
+      inbound_request_responses: inbound_request_responses_send,
+    }))
+  }
+}
+
+impl tributary_sdk::P2p for Libp2p {
+  fn broadcast(&self, tributary: [u8; 32], message: Vec<u8>) -> impl Send + Future<Output = ()> {
+    async move {
+      self
+        .0
+        .gossip
+        .send(Message::Tributary { tributary, message })
+        .expect("gossip recv channel was dropped?");
+    }
+  }
+}
+
+impl serai_cosign::RequestNotableCosigns for Libp2p {
+  type Error = ();
+
+  fn request_notable_cosigns(
+    &self,
+    global_session: [u8; 32],
+  ) -> impl Send + Future<Output = Result<(), Self::Error>> {
+    async move {
+      const AMOUNT_OF_PEERS_TO_REQUEST_FROM: usize = 3;
+      const NOTABLE_COSIGNS_TIMEOUT: Duration = Duration::from_secs(5);
+
+      let request = Request::NotableCosigns { global_session };
+
+      let peers = self.0.peers.peers.read().await.clone();
+      // HashSet of all peers
+      let peers = peers.into_values().flat_map(<_>::into_iter).collect::<HashSet<_>>();
+      // Vec of all peers
+      let mut peers = peers.into_iter().collect::<Vec<_>>();
+
+      let mut channels = Vec::with_capacity(AMOUNT_OF_PEERS_TO_REQUEST_FROM);
+      for _ in 0 .. AMOUNT_OF_PEERS_TO_REQUEST_FROM {
+        if peers.is_empty() {
+          break;
+        }
+        let i = usize::try_from(OsRng.next_u64() % u64::try_from(peers.len()).unwrap()).unwrap();
+        let peer = peers.swap_remove(i);
+
+        let (sender, receiver) = oneshot::channel();
+        self
+          .0
+          .outbound_requests
+          .send((peer, request, sender))
+          .expect("outbound requests recv channel was dropped?");
+        channels.push(receiver);
+      }
+
+      // We could reduce our latency by using FuturesUnordered here but the latency isn't a concern
+      for channel in channels {
+        if let Ok(Ok(Response::NotableCosigns(cosigns))) =
+          tokio::time::timeout(NOTABLE_COSIGNS_TIMEOUT, channel).await
+        {
+          for cosign in cosigns {
+            self
+              .0
+              .signed_cosigns_send
+              .send(cosign)
+              .expect("signed_cosigns recv in this object was dropped?");
+          }
+        }
+      }
+
+      Ok(())
+    }
+  }
+}
+
+impl serai_coordinator_p2p::P2p for Libp2p {
+  type Peer<'a> = Peer<'a>;
+
+  fn peers(&self, network: NetworkId) -> impl Send + Future<Output = Vec<Self::Peer<'_>>> {
+    async move {
+      let Some(peer_ids) = self.0.peers.peers.read().await.get(&network).cloned() else {
+        return vec![];
+      };
+      let mut res = vec![];
+      for id in peer_ids {
+        res.push(Peer { outbound_requests: &self.0.outbound_requests, id });
+      }
+      res
+    }
+  }
+
+  fn publish_cosign(&self, cosign: SignedCosign) -> impl Send + Future<Output = ()> {
+    async move {
+      self.0.gossip.send(Message::Cosign(cosign)).expect("gossip recv channel was dropped?");
+    }
+  }
+
+  fn heartbeat(
+    &self,
+  ) -> impl Send + Future<Output = (Heartbeat, oneshot::Sender<Vec<TributaryBlockWithCommit>>)> {
+    async move {
+      let (request_id, set, latest_block_hash) = self
+        .0
+        .heartbeat_requests
+        .lock()
+        .await
+        .recv()
+        .await
+        .expect("heartbeat_requests_send was dropped?");
+      let (sender, receiver) = oneshot::channel();
+      tokio::spawn({
+        let respond = self.0.inbound_request_responses.clone();
+        async move {
+          // The swarm task expects us to respond to every request. If the caller drops this
+          // channel, we'll receive `Err` and respond with `vec![]`, safely satisfying that bound
+          // without requiring the caller send a value down this channel
+          let response = if let Ok(blocks) = receiver.await {
+            Response::Blocks(blocks)
+          } else {
+            Response::Blocks(vec![])
+          };
+          respond
+            .send((request_id, response))
+            .expect("inbound_request_responses_recv was dropped?");
+        }
+      });
+      (Heartbeat { set, latest_block_hash }, sender)
+    }
+  }
+
+  fn notable_cosigns_request(
+    &self,
+  ) -> impl Send + Future<Output = ([u8; 32], oneshot::Sender<Vec<SignedCosign>>)> {
+    async move {
+      let (request_id, global_session) = self
+        .0
+        .notable_cosign_requests
+        .lock()
+        .await
+        .recv()
+        .await
+        .expect("notable_cosign_requests_send was dropped?");
+      let (sender, receiver) = oneshot::channel();
+      tokio::spawn({
+        let respond = self.0.inbound_request_responses.clone();
+        async move {
+          let response = if let Ok(notable_cosigns) = receiver.await {
+            Response::NotableCosigns(notable_cosigns)
+          } else {
+            Response::NotableCosigns(vec![])
+          };
+          respond
+            .send((request_id, response))
+            .expect("inbound_request_responses_recv was dropped?");
+        }
+      });
+      (global_session, sender)
+    }
+  }
+
+  fn tributary_message(&self) -> impl Send + Future<Output = ([u8; 32], Vec<u8>)> {
+    async move {
+      self.0.tributary_gossip.lock().await.recv().await.expect("tributary_gossip send was dropped?")
+    }
+  }
+
+  fn cosign(&self) -> impl Send + Future<Output = SignedCosign> {
+    async move {
+      self
+        .0
+        .signed_cosigns
+        .lock()
+        .await
+        .recv()
+        .await
+        .expect("signed_cosigns couldn't recv despite send in same object?")
+    }
+  }
+}

coordinator/p2p/libp2p/src/ping.rs

@@ -0,0 +1,17 @@
+use core::time::Duration;
+
+use tributary_sdk::tendermint::LATENCY_TIME;
+
+use libp2p::ping::{self, Config, Behaviour};
+pub use ping::Event;
+
+pub(crate) const INTERVAL: Duration = Duration::from_secs(30);
+// LATENCY_TIME represents the maximum latency for message delivery. Sending the ping, and
+// receiving the pong, each have to occur within this time bound to validate the connection. We
+// enforce that, as best we can, by requiring the round-trip be within twice the allowed latency.
+pub(crate) const TIMEOUT: Duration = Duration::from_millis((2 * LATENCY_TIME) as u64);
+
+pub(crate) type Behavior = Behaviour;
+pub(crate) fn new_behavior() -> Behavior {
+  Behavior::new(Config::default().with_interval(INTERVAL).with_timeout(TIMEOUT))
+}

coordinator/p2p/libp2p/src/reqres.rs

@@ -4,36 +4,33 @@ use std::io;
 use async_trait::async_trait;
 
 use borsh::{BorshSerialize, BorshDeserialize};
-use serai_client::validator_sets::primitives::ValidatorSet;
 
 use futures_util::{AsyncRead, AsyncReadExt, AsyncWrite, AsyncWriteExt};
 
 use libp2p::request_response::{
   self, Codec as CodecTrait, Event as GenericEvent, Config, Behaviour, ProtocolSupport,
 };
-pub use request_response::Message;
+pub use request_response::{RequestId, Message};
 
 use serai_cosign::SignedCosign;
 
-use crate::p2p::TributaryBlockWithCommit;
+use serai_coordinator_p2p::{Heartbeat, TributaryBlockWithCommit};
 
 /// The maximum message size for the request-response protocol
 // This is derived from the heartbeat message size as it's our largest message
 pub(crate) const MAX_LIBP2P_REQRES_MESSAGE_SIZE: usize =
-  (tributary::BLOCK_SIZE_LIMIT * crate::p2p::heartbeat::BLOCKS_PER_BATCH) + 1024;
+  1024 + serai_coordinator_p2p::heartbeat::BATCH_SIZE_LIMIT;
 
 const PROTOCOL: &str = "/serai/coordinator/reqres/1.0.0";
 
 /// Requests which can be made via the request-response protocol.
 #[derive(Clone, Copy, Debug, BorshSerialize, BorshDeserialize)]
 pub(crate) enum Request {
-  /// A keep-alive to prevent our connections from being dropped.
-  KeepAlive,
   /// A heartbeat informing our peers of our latest block, for the specified blockchain, on regular
   /// intervals.
   ///
   /// If our peers have more blocks than us, they're expected to respond with those blocks.
-  Heartbeat { set: ValidatorSet, latest_block_hash: [u8; 32] },
+  Heartbeat(Heartbeat),
   /// A request for the notable cosigns for a global session.
   NotableCosigns { global_session: [u8; 32] },
 }
@@ -105,7 +102,7 @@ impl CodecTrait for Codec {
   }
   async fn read_response<R: Send + Unpin + AsyncRead>(
     &mut self,
-    proto: &Self::Protocol,
+    _: &Self::Protocol,
     io: &mut R,
   ) -> io::Result<Response> {
     Self::read(io).await
@@ -120,7 +117,7 @@ impl CodecTrait for Codec {
   }
   async fn write_response<W: Send + Unpin + AsyncWrite>(
     &mut self,
-    proto: &Self::Protocol,
+    _: &Self::Protocol,
     io: &mut W,
     res: Response,
   ) -> io::Result<()> {

coordinator/p2p/libp2p/src/swarm.rs

@@ -21,14 +21,16 @@ use libp2p::{
   swarm::{dial_opts::DialOpts, SwarmEvent, Swarm},
 };
 
-use crate::p2p::libp2p::{
+use serai_coordinator_p2p::Heartbeat;
+
+use crate::{
   Peers, BehaviorEvent, Behavior,
-  validators::Validators,
+  validators::{self, Validators},
+  ping,
   reqres::{self, Request, Response},
   gossip,
 };
 
-const KEEP_ALIVE_INTERVAL: Duration = Duration::from_secs(80);
 const TIME_BETWEEN_REBUILD_PEERS: Duration = Duration::from_secs(10 * 60);
 
 /*
@@ -52,27 +54,21 @@ pub(crate) struct SwarmTask {
   last_dial_task_run: Instant,
 
   validators: Arc<RwLock<Validators>>,
+  validator_changes: mpsc::UnboundedReceiver<validators::Changes>,
   peers: Peers,
   rebuild_peers_at: Instant,
 
   swarm: Swarm<Behavior>,
 
-  last_message: Instant,
-
   gossip: mpsc::UnboundedReceiver<gossip::Message>,
   signed_cosigns: mpsc::UnboundedSender<SignedCosign>,
-  tributary_gossip: mpsc::UnboundedSender<(ValidatorSet, Vec<u8>)>,
+  tributary_gossip: mpsc::UnboundedSender<([u8; 32], Vec<u8>)>,
 
   outbound_requests: mpsc::UnboundedReceiver<(PeerId, Request, oneshot::Sender<Response>)>,
   outbound_request_responses: HashMap<RequestId, oneshot::Sender<Response>>,
 
   inbound_request_response_channels: HashMap<RequestId, ResponseChannel<Response>>,
   heartbeat_requests: mpsc::UnboundedSender<(RequestId, ValidatorSet, [u8; 32])>,
-  /* TODO
-    let cosigns = Cosigning::<D>::notable_cosigns(&self.db, global_session);
-    let res = reqres::Response::NotableCosigns(cosigns);
-    let _: Result<_, _> = self.swarm.behaviour_mut().reqres.send_response(channel, res);
-  */
   notable_cosign_requests: mpsc::UnboundedSender<(RequestId, [u8; 32])>,
   inbound_request_responses: mpsc::UnboundedReceiver<(RequestId, Response)>,
 }
@@ -82,12 +78,13 @@ impl SwarmTask {
     match event {
       gossip::Event::Message { message, .. } => {
         let Ok(message) = gossip::Message::deserialize(&mut message.data.as_slice()) else {
-          // TODO: Penalize the PeerId which sent this message
+          // TODO: Penalize the PeerId which created this message, which requires authenticating
+          // each message OR moving to explicit acknowledgement before re-gossiping
           return;
         };
         match message {
-          gossip::Message::Tributary { set, message } => {
-            let _: Result<_, _> = self.tributary_gossip.send((set, message));
+          gossip::Message::Tributary { tributary, message } => {
+            let _: Result<_, _> = self.tributary_gossip.send((tributary, message));
           }
           gossip::Message::Cosign(signed_cosign) => {
             let _: Result<_, _> = self.signed_cosigns.send(signed_cosign);
@@ -105,11 +102,7 @@ impl SwarmTask {
     match event {
       reqres::Event::Message { message, .. } => match message {
         reqres::Message::Request { request_id, request, channel } => match request {
-          reqres::Request::KeepAlive => {
-            let _: Result<_, _> =
-              self.swarm.behaviour_mut().reqres.send_response(channel, Response::None);
-          }
-          reqres::Request::Heartbeat { set, latest_block_hash } => {
+          reqres::Request::Heartbeat(Heartbeat { set, latest_block_hash }) => {
             self.inbound_request_response_channels.insert(request_id, channel);
             let _: Result<_, _> =
               self.heartbeat_requests.send((request_id, set, latest_block_hash));
@@ -137,17 +130,19 @@ impl SwarmTask {
 
   async fn run(mut self) {
     loop {
-      let time_till_keep_alive = Instant::now().saturating_duration_since(self.last_message);
       let time_till_rebuild_peers = self.rebuild_peers_at.saturating_duration_since(Instant::now());
 
       tokio::select! {
-        () = tokio::time::sleep(time_till_keep_alive) => {
-          let peers = self.swarm.connected_peers().copied().collect::<Vec<_>>();
-          let behavior = self.swarm.behaviour_mut();
-          for peer in peers {
-            behavior.reqres.send_request(&peer, Request::KeepAlive);
+        // If the validators have changed, update the allow list
+        validator_changes = self.validator_changes.recv() => {
+          let validator_changes = validator_changes.expect("validators update task shut down?");
+          let behavior = &mut self.swarm.behaviour_mut().allow_list;
+          for removed in validator_changes.removed {
+            behavior.disallow_peer(removed);
+          }
+          for added in validator_changes.added {
+            behavior.allow_peer(added);
           }
-          self.last_message = Instant::now();
         }
 
         // Dial peers we're instructed to
@@ -170,26 +165,15 @@ impl SwarmTask {
           let validators_by_network = self.validators.read().await.by_network().clone();
           let connected_peers = self.swarm.connected_peers().copied().collect::<HashSet<_>>();
 
-          // We initially populate the list of peers to disconnect with all peers
-          let mut to_disconnect = connected_peers.clone();
-
           // Build the new peers object
           let mut peers = HashMap::new();
           for (network, validators) in validators_by_network {
             peers.insert(network, validators.intersection(&connected_peers).copied().collect());
-
-            // If this peer is in this validator set, don't keep it flagged for disconnection
-            to_disconnect.retain(|peer| !validators.contains(peer));
           }
 
           // Write the new peers object
           *self.peers.peers.write().await = peers;
           self.rebuild_peers_at = Instant::now() + TIME_BETWEEN_REBUILD_PEERS;
-
-          // Disconnect all peers marked for disconnection
-          for peer in to_disconnect {
-            let _: Result<_, _> = self.swarm.disconnect_peer_id(peer);
-          }
         }
 
         // Handle swarm events
@@ -238,6 +222,19 @@ impl SwarmTask {
               }
             }
 
+            SwarmEvent::Behaviour(
+              BehaviorEvent::AllowList(event) | BehaviorEvent::ConnectionLimits(event)
+            ) => {
+              // This *is* an exhaustive match as these events are empty enums
+              match event {}
+            }
+            SwarmEvent::Behaviour(
+              BehaviorEvent::Ping(ping::Event { peer: _, connection, result, })
+            ) => {
+              if result.is_err() {
+                self.swarm.close_connection(connection);
+              }
+            }
             SwarmEvent::Behaviour(BehaviorEvent::Reqres(event)) => {
               self.handle_reqres(event)
             }
@@ -261,8 +258,31 @@ impl SwarmTask {
           let message = message.expect("channel for messages to gossip was closed?");
           let topic = message.topic();
           let message = borsh::to_vec(&message).unwrap();
-          let _: Result<_, _> = self.swarm.behaviour_mut().gossip.publish(topic, message);
-          self.last_message = Instant::now();
+
+          /*
+            If we're sending a message for this topic, it's because this topic is relevant to us.
+            Subscribe to it.
+
+            We create topics roughly weekly, one per validator set/session. Once present in a
+            topic, we're interested in all messages for it until the validator set/session retires.
+            Then there should no longer be any messages for the topic as we should drop the
+            Tributary which creates the messages.
+
+            We use this as an argument to not bother implement unsubscribing from topics. They're
+            incredibly infrequently created and old topics shouldn't still have messages published
+            to them. Having the coordinator reboot being our method of unsubscribing is fine.
+
+            Alternatively, we could route an API to determine when a topic is retired, or retire
+            any topics we haven't sent messages on in the past hour.
+          */
+          let behavior = self.swarm.behaviour_mut();
+          let _: Result<_, _> = behavior.gossip.subscribe(&topic);
+          /*
+            This may be an error of `InsufficientPeers`. If so, we could ask DialTask to dial more
+            peers for this network. We don't as we assume DialTask will detect the lack of peers
+            for this network, and will already successfully handle this.
+          */
+          let _: Result<_, _> = behavior.gossip.publish(topic.hash(), message);
         }
 
         request = self.outbound_requests.recv() => {
@@ -290,13 +310,14 @@ impl SwarmTask {
     to_dial: mpsc::UnboundedReceiver<DialOpts>,
 
     validators: Arc<RwLock<Validators>>,
+    validator_changes: mpsc::UnboundedReceiver<validators::Changes>,
     peers: Peers,
 
     swarm: Swarm<Behavior>,
 
     gossip: mpsc::UnboundedReceiver<gossip::Message>,
     signed_cosigns: mpsc::UnboundedSender<SignedCosign>,
-    tributary_gossip: mpsc::UnboundedSender<(ValidatorSet, Vec<u8>)>,
+    tributary_gossip: mpsc::UnboundedSender<([u8; 32], Vec<u8>)>,
 
     outbound_requests: mpsc::UnboundedReceiver<(PeerId, Request, oneshot::Sender<Response>)>,
 
@@ -311,13 +332,12 @@ impl SwarmTask {
         last_dial_task_run: Instant::now(),
 
         validators,
+        validator_changes,
         peers,
         rebuild_peers_at: Instant::now() + TIME_BETWEEN_REBUILD_PEERS,
 
         swarm,
 
-        last_message: Instant::now(),
-
         gossip,
         signed_cosigns,
         tributary_gossip,

coordinator/p2p/libp2p/src/validators.rs

@@ -4,19 +4,24 @@ use std::{
   collections::{HashSet, HashMap},
 };
 
-use serai_client::{primitives::NetworkId, validator_sets::primitives::Session, Serai};
+use serai_client::{primitives::NetworkId, validator_sets::primitives::Session, SeraiError, Serai};
 
 use serai_task::{Task, ContinuallyRan};
 
 use libp2p::PeerId;
 
 use futures_util::stream::{StreamExt, FuturesUnordered};
-use tokio::sync::RwLock;
+use tokio::sync::{mpsc, RwLock};
 
-use crate::p2p::libp2p::peer_id_from_public;
+use crate::peer_id_from_public;
+
+pub(crate) struct Changes {
+  pub(crate) removed: HashSet<PeerId>,
+  pub(crate) added: HashSet<PeerId>,
+}
 
 pub(crate) struct Validators {
-  serai: Serai,
+  serai: Arc<Serai>,
 
   // A cache for which session we're populated with the validators of
   sessions: HashMap<NetworkId, Session>,
@@ -24,24 +29,29 @@ pub(crate) struct Validators {
   by_network: HashMap<NetworkId, HashSet<PeerId>>,
   // The validators and their networks
   validators: HashMap<PeerId, HashSet<NetworkId>>,
+
+  // The channel to send the changes down
+  changes: mpsc::UnboundedSender<Changes>,
 }
 
 impl Validators {
-  pub(crate) fn new(serai: Serai) -> Self {
-    Validators {
+  pub(crate) fn new(serai: Arc<Serai>) -> (Self, mpsc::UnboundedReceiver<Changes>) {
+    let (send, recv) = mpsc::unbounded_channel();
+    let validators = Validators {
       serai,
       sessions: HashMap::new(),
       by_network: HashMap::new(),
       validators: HashMap::new(),
-    }
+      changes: send,
+    };
+    (validators, recv)
   }
 
   async fn session_changes(
     serai: impl Borrow<Serai>,
     sessions: impl Borrow<HashMap<NetworkId, Session>>,
-  ) -> Result<Vec<(NetworkId, Session, HashSet<PeerId>)>, String> {
-    let temporal_serai =
-      serai.borrow().as_of_latest_finalized_block().await.map_err(|e| format!("{e:?}"))?;
+  ) -> Result<Vec<(NetworkId, Session, HashSet<PeerId>)>, SeraiError> {
+    let temporal_serai = serai.borrow().as_of_latest_finalized_block().await?;
     let temporal_serai = temporal_serai.validator_sets();
 
     let mut session_changes = vec![];
@@ -58,7 +68,7 @@ impl Validators {
           let session = match temporal_serai.session(network).await {
             Ok(Some(session)) => session,
             Ok(None) => return Ok(None),
-            Err(e) => return Err(format!("{e:?}")),
+            Err(e) => return Err(e),
           };
 
           if sessions.get(&network) == Some(&session) {
@@ -70,7 +80,7 @@ impl Validators {
                 session,
                 validators.into_iter().map(peer_id_from_public).collect(),
               ))),
-              Err(e) => Err(format!("{e:?}")),
+              Err(e) => Err(e),
             }
           }
         });
@@ -89,6 +99,9 @@ impl Validators {
     &mut self,
     session_changes: Vec<(NetworkId, Session, HashSet<PeerId>)>,
   ) {
+    let mut removed = HashSet::new();
+    let mut added = HashSet::new();
+
     for (network, session, validators) in session_changes {
       // Remove the existing validators
       for validator in self.by_network.remove(&network).unwrap_or_else(HashSet::new) {
@@ -96,26 +109,45 @@ impl Validators {
         let mut networks = self.validators.remove(&validator).unwrap();
         // Remove this one
         networks.remove(&network);
-        // Insert the networks back if the validator was present in other networks
         if !networks.is_empty() {
+          // Insert the networks back if the validator was present in other networks
           self.validators.insert(validator, networks);
+        } else {
+          // Because this validator is no longer present in any network, mark them as removed
+          /*
+            This isn't accurate. The validator isn't present in the latest session for this
+            network. The validator was present in the prior session which has yet to retire. Our
+            lack of explicit inclusion for both the prior session and the current session causes
+            only the validators mutually present in both sessions to be responsible for all actions
+            still ongoing as the prior validator set retires.
+
+            TODO: Fix this
+          */
+          removed.insert(validator);
         }
       }
 
       // Add the new validators
       for validator in validators.iter().copied() {
         self.validators.entry(validator).or_insert_with(HashSet::new).insert(network);
+        added.insert(validator);
       }
       self.by_network.insert(network, validators);
 
       // Update the session we have populated
       self.sessions.insert(network, session);
     }
+
+    // Only flag validators for removal if they weren't simultaneously added by these changes
+    removed.retain(|validator| !added.contains(validator));
+    // Send the changes, dropping the error
+    // This lets the caller opt-out of change notifications by dropping the receiver
+    let _: Result<_, _> = self.changes.send(Changes { removed, added });
   }
 
   /// Update the view of the validators.
-  pub(crate) async fn update(&mut self) -> Result<(), String> {
-    let session_changes = Self::session_changes(&self.serai, &self.sessions).await?;
+  pub(crate) async fn update(&mut self) -> Result<(), SeraiError> {
+    let session_changes = Self::session_changes(&*self.serai, &self.sessions).await?;
     self.incorporate_session_changes(session_changes);
     Ok(())
   }
@@ -124,10 +156,6 @@ impl Validators {
     &self.by_network
   }
 
-  pub(crate) fn contains(&self, peer_id: &PeerId) -> bool {
-    self.validators.contains_key(peer_id)
-  }
-
   pub(crate) fn networks(&self, peer_id: &PeerId) -> Option<&HashSet<NetworkId>> {
     self.validators.get(peer_id)
   }
@@ -145,9 +173,12 @@ impl UpdateValidatorsTask {
   /// Spawn a new instance of the UpdateValidatorsTask.
   ///
   /// This returns a reference to the Validators it updates after spawning itself.
-  pub(crate) fn spawn(serai: Serai) -> Arc<RwLock<Validators>> {
+  pub(crate) fn spawn(
+    serai: Arc<Serai>,
+  ) -> (Arc<RwLock<Validators>>, mpsc::UnboundedReceiver<Changes>) {
     // The validators which will be updated
-    let validators = Arc::new(RwLock::new(Validators::new(serai)));
+    let (validators, changes) = Validators::new(serai);
+    let validators = Arc::new(RwLock::new(validators));
 
     // Define the task
     let (update_validators_task, update_validators_task_handle) = Task::new();
@@ -159,7 +190,7 @@ impl UpdateValidatorsTask {
     );
 
     // Return the validators
-    validators
+    (validators, changes)
   }
 }
 
@@ -168,13 +199,13 @@ impl ContinuallyRan for UpdateValidatorsTask {
   const DELAY_BETWEEN_ITERATIONS: u64 = 60;
   const MAX_DELAY_BETWEEN_ITERATIONS: u64 = 5 * 60;
 
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = SeraiError;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       let session_changes = {
         let validators = self.validators.read().await;
-        Validators::session_changes(validators.serai.clone(), validators.sessions.clone())
-          .await
-          .map_err(|e| format!("{e:?}"))?
+        Validators::session_changes(validators.serai.clone(), validators.sessions.clone()).await?
       };
       self.validators.write().await.incorporate_session_changes(session_changes);
       Ok(true)

coordinator/p2p/src/heartbeat.rs

@@ -1,40 +1,53 @@
 use core::future::Future;
 use std::time::{Duration, SystemTime};
 
-use serai_client::validator_sets::primitives::ValidatorSet;
+use serai_client::validator_sets::primitives::{MAX_KEY_SHARES_PER_SET, ValidatorSet};
 
-use futures_util::FutureExt;
+use futures_lite::FutureExt;
 
-use tributary::{ReadWrite, Block, Tributary, TributaryReader};
+use tributary_sdk::{ReadWrite, TransactionTrait, Block, Tributary, TributaryReader};
 
 use serai_db::*;
 use serai_task::ContinuallyRan;
 
-use crate::{
-  tributary::Transaction,
-  p2p::{Peer, P2p},
-};
+use crate::{Heartbeat, Peer, P2p};
 
 // Amount of blocks in a minute
-const BLOCKS_PER_MINUTE: usize = (60 / (tributary::tendermint::TARGET_BLOCK_TIME / 1000)) as usize;
+const BLOCKS_PER_MINUTE: usize =
+  (60 / (tributary_sdk::tendermint::TARGET_BLOCK_TIME / 1000)) as usize;
 
-// Maximum amount of blocks to send in a batch of blocks
-pub const BLOCKS_PER_BATCH: usize = BLOCKS_PER_MINUTE + 1;
+/// The minimum amount of blocks to include/included within a batch, assuming there's blocks to
+/// include in the batch.
+///
+/// This decides the size limit of the Batch (the Block size limit multiplied by the minimum amount
+/// of blocks we'll send). The actual amount of blocks sent will be the amount which fits within
+/// the size limit.
+pub const MIN_BLOCKS_PER_BATCH: usize = BLOCKS_PER_MINUTE + 1;
+
+/// The size limit for a batch of blocks sent in response to a Heartbeat.
+///
+/// This estimates the size of a commit as `32 + (MAX_VALIDATORS * 128)`. At the time of writing, a
+/// commit is `8 + (validators * 32) + (32 + (validators * 32))` (for the time, list of validators,
+/// and aggregate signature). Accordingly, this should be a safe over-estimate.
+pub const BATCH_SIZE_LIMIT: usize = MIN_BLOCKS_PER_BATCH *
+  (tributary_sdk::BLOCK_SIZE_LIMIT + 32 + ((MAX_KEY_SHARES_PER_SET as usize) * 128));
 
 /// Sends a heartbeat to other validators on regular intervals informing them of our Tributary's
 /// tip.
 ///
 /// If the other validator has more blocks then we do, they're expected to inform us. This forms
 /// the sync protocol for our Tributaries.
-struct HeartbeatTask<TD: Db, P: P2p> {
-  set: ValidatorSet,
-  tributary: Tributary<TD, Transaction, P>,
-  reader: TributaryReader<TD, Transaction>,
-  p2p: P,
+pub(crate) struct HeartbeatTask<TD: Db, Tx: TransactionTrait, P: P2p> {
+  pub(crate) set: ValidatorSet,
+  pub(crate) tributary: Tributary<TD, Tx, P>,
+  pub(crate) reader: TributaryReader<TD, Tx>,
+  pub(crate) p2p: P,
 }
 
-impl<TD: Db, P: P2p> ContinuallyRan for HeartbeatTask<TD, P> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+impl<TD: Db, Tx: TransactionTrait, P: P2p> ContinuallyRan for HeartbeatTask<TD, Tx, P> {
+  type Error = String;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       // If our blockchain hasn't had a block in the past minute, trigger the heartbeat protocol
       const TIME_TO_TRIGGER_SYNCING: Duration = Duration::from_secs(60);
@@ -73,13 +86,17 @@ impl<TD: Db, P: P2p> ContinuallyRan for HeartbeatTask<TD, P> {
               tip_is_stale = false;
             }
             // Necessary due to https://github.com/rust-lang/rust/issues/100013
-            let Some(blocks) = peer.send_heartbeat(self.set, tip).boxed().await else {
+            let Some(blocks) = peer
+              .send_heartbeat(Heartbeat { set: self.set, latest_block_hash: tip })
+              .boxed()
+              .await
+            else {
               continue 'peer;
             };
 
             // This is the final batch if it has less than the maximum amount of blocks
             // (signifying there weren't more blocks after this to fill the batch with)
-            let final_batch = blocks.len() < BLOCKS_PER_BATCH;
+            let final_batch = blocks.len() < MIN_BLOCKS_PER_BATCH;
 
             // Sync each block
             for block_with_commit in blocks {
@@ -91,7 +108,14 @@ impl<TD: Db, P: P2p> ContinuallyRan for HeartbeatTask<TD, P> {
 
               // Attempt to sync the block
               if !self.tributary.sync_block(block, block_with_commit.commit).await {
-                // The block may be invalid or may simply be stale
+                // The block may be invalid or stale if we added a block elsewhere
+                if (!tip_is_stale) && (tip != self.reader.tip()) {
+                  // Since the Tributary's tip advanced on its own, return
+                  return Ok(false);
+                }
+
+                // Since this block was invalid or stale in a way non-trivial to detect, try to
+                // sync with the next peer
                 continue 'peer;
               }
 

coordinator/p2p/src/lib.rs

@@ -0,0 +1,204 @@
+#![cfg_attr(docsrs, feature(doc_auto_cfg))]
+#![doc = include_str!("../README.md")]
+#![deny(missing_docs)]
+
+use core::future::Future;
+use std::collections::HashMap;
+
+use borsh::{BorshSerialize, BorshDeserialize};
+
+use serai_client::{primitives::NetworkId, validator_sets::primitives::ValidatorSet};
+
+use serai_db::Db;
+use tributary_sdk::{ReadWrite, TransactionTrait, Tributary, TributaryReader};
+use serai_cosign::{SignedCosign, Cosigning};
+
+use tokio::sync::{mpsc, oneshot};
+
+use serai_task::{Task, ContinuallyRan};
+
+/// The heartbeat task, effecting sync of Tributaries
+pub mod heartbeat;
+use crate::heartbeat::HeartbeatTask;
+
+/// A heartbeat for a Tributary.
+#[derive(Clone, Copy, BorshSerialize, BorshDeserialize, Debug)]
+pub struct Heartbeat {
+  /// The Tributary this is the heartbeat of.
+  pub set: ValidatorSet,
+  /// The hash of the latest block added to the Tributary.
+  pub latest_block_hash: [u8; 32],
+}
+
+/// A tributary block and its commit.
+#[derive(Clone, BorshSerialize, BorshDeserialize)]
+pub struct TributaryBlockWithCommit {
+  /// The serialized block.
+  pub block: Vec<u8>,
+  /// The serialized commit.
+  pub commit: Vec<u8>,
+}
+
+/// A representation of a peer.
+pub trait Peer<'a>: Send {
+  /// Send a heartbeat to this peer.
+  fn send_heartbeat(
+    &self,
+    heartbeat: Heartbeat,
+  ) -> impl Send + Future<Output = Option<Vec<TributaryBlockWithCommit>>>;
+}
+
+/// The representation of the P2P network.
+pub trait P2p:
+  Send + Sync + Clone + tributary_sdk::P2p + serai_cosign::RequestNotableCosigns
+{
+  /// The representation of a peer.
+  type Peer<'a>: Peer<'a>;
+
+  /// Fetch the peers for this network.
+  fn peers(&self, network: NetworkId) -> impl Send + Future<Output = Vec<Self::Peer<'_>>>;
+
+  /// Broadcast a cosign.
+  fn publish_cosign(&self, cosign: SignedCosign) -> impl Send + Future<Output = ()>;
+
+  /// A cancel-safe future for the next heartbeat received over the P2P network.
+  ///
+  /// Yields the validator set its for, the latest block hash observed, and a channel to return the
+  /// descending blocks. This channel MUST NOT and will not have its receiver dropped before a
+  /// message is sent.
+  fn heartbeat(
+    &self,
+  ) -> impl Send + Future<Output = (Heartbeat, oneshot::Sender<Vec<TributaryBlockWithCommit>>)>;
+
+  /// A cancel-safe future for the next request for the notable cosigns of a gloabl session.
+  ///
+  /// Yields the global session the request is for and a channel to return the notable cosigns.
+  /// This channel MUST NOT and will not have its receiver dropped before a message is sent.
+  fn notable_cosigns_request(
+    &self,
+  ) -> impl Send + Future<Output = ([u8; 32], oneshot::Sender<Vec<SignedCosign>>)>;
+
+  /// A cancel-safe future for the next message regarding a Tributary.
+  ///
+  /// Yields the message's Tributary's genesis block hash and the message.
+  fn tributary_message(&self) -> impl Send + Future<Output = ([u8; 32], Vec<u8>)>;
+
+  /// A cancel-safe future for the next cosign received.
+  fn cosign(&self) -> impl Send + Future<Output = SignedCosign>;
+}
+
+fn handle_notable_cosigns_request<D: Db>(
+  db: &D,
+  global_session: [u8; 32],
+  channel: oneshot::Sender<Vec<SignedCosign>>,
+) {
+  let cosigns = Cosigning::<D>::notable_cosigns(db, global_session);
+  channel.send(cosigns).expect("channel listening for cosign oneshot response was dropped?");
+}
+
+fn handle_heartbeat<D: Db, T: TransactionTrait>(
+  reader: &TributaryReader<D, T>,
+  mut latest_block_hash: [u8; 32],
+  channel: oneshot::Sender<Vec<TributaryBlockWithCommit>>,
+) {
+  let mut res_size = 8;
+  let mut res = vec![];
+  // This former case should be covered by this latter case
+  while (res.len() < heartbeat::MIN_BLOCKS_PER_BATCH) || (res_size < heartbeat::BATCH_SIZE_LIMIT) {
+    let Some(block_after) = reader.block_after(&latest_block_hash) else { break };
+
+    // These `break` conditions should only occur under edge cases, such as if we're actively
+    // deleting this Tributary due to being done with it
+    let Some(block) = reader.block(&block_after) else { break };
+    let block = block.serialize();
+    let Some(commit) = reader.commit(&block_after) else { break };
+    res_size += 8 + block.len() + 8 + commit.len();
+    res.push(TributaryBlockWithCommit { block, commit });
+
+    latest_block_hash = block_after;
+  }
+  channel
+    .send(res)
+    .map_err(|_| ())
+    .expect("channel listening for heartbeat oneshot response was dropped?");
+}
+
+/// Run the P2P instance.
+///
+/// `add_tributary`'s and `retire_tributary's senders, along with `send_cosigns`'s receiver, must
+/// never be dropped. `retire_tributary` is not required to only be instructed with added
+/// Tributaries.
+pub async fn run<TD: Db, Tx: TransactionTrait, P: P2p>(
+  db: impl Db,
+  p2p: P,
+  mut add_tributary: mpsc::UnboundedReceiver<(ValidatorSet, Tributary<TD, Tx, P>)>,
+  mut retire_tributary: mpsc::UnboundedReceiver<ValidatorSet>,
+  send_cosigns: mpsc::UnboundedSender<SignedCosign>,
+) {
+  let mut readers = HashMap::<ValidatorSet, TributaryReader<TD, Tx>>::new();
+  let mut tributaries = HashMap::<[u8; 32], mpsc::UnboundedSender<Vec<u8>>>::new();
+  let mut heartbeat_tasks = HashMap::<ValidatorSet, _>::new();
+
+  loop {
+    tokio::select! {
+      tributary = add_tributary.recv() => {
+        let (set, tributary) = tributary.expect("add_tributary send was dropped");
+        let reader = tributary.reader();
+        readers.insert(set, reader.clone());
+
+        let (heartbeat_task_def, heartbeat_task) = Task::new();
+        tokio::spawn(
+          (HeartbeatTask {
+            set,
+            tributary: tributary.clone(),
+            reader: reader.clone(),
+            p2p: p2p.clone(),
+          }).continually_run(heartbeat_task_def, vec![])
+        );
+        heartbeat_tasks.insert(set, heartbeat_task);
+
+        let (tributary_message_send, mut tributary_message_recv) = mpsc::unbounded_channel();
+        tributaries.insert(tributary.genesis(), tributary_message_send);
+        // For as long as this sender exists, handle the messages from it on a dedicated task
+        tokio::spawn(async move {
+          while let Some(message) = tributary_message_recv.recv().await {
+            tributary.handle_message(&message).await;
+          }
+        });
+      }
+      set = retire_tributary.recv() => {
+        let set = set.expect("retire_tributary send was dropped");
+        let Some(reader) = readers.remove(&set) else { continue };
+        tributaries.remove(&reader.genesis()).expect("tributary reader but no tributary");
+        heartbeat_tasks.remove(&set).expect("tributary but no heartbeat task");
+      }
+
+      (heartbeat, channel) = p2p.heartbeat() => {
+        if let Some(reader) = readers.get(&heartbeat.set) {
+          let reader = reader.clone(); // This is a cheap clone
+          // We spawn this on a task due to the DB reads needed
+          tokio::spawn(async move {
+            handle_heartbeat(&reader, heartbeat.latest_block_hash, channel)
+          });
+        }
+      }
+      (global_session, channel) = p2p.notable_cosigns_request() => {
+        tokio::spawn({
+          let db = db.clone();
+          async move { handle_notable_cosigns_request(&db, global_session, channel) }
+        });
+      }
+      (tributary, message) = p2p.tributary_message() => {
+        if let Some(tributary) = tributaries.get(&tributary) {
+          tributary.send(message).expect("tributary message recv was dropped?");
+        }
+      }
+      cosign = p2p.cosign() => {
+        // We don't call `Cosigning::intake_cosign` here as that can only be called from a single
+        // location. We also need to intake the cosigns we produce, which means we need to merge
+        // these streams (signing, network) somehow. That's done with this mpsc channel
+        send_cosigns.send(cosign).expect("channel receiving cosigns was dropped");
+      }
+    }
+  }
+}

coordinator/src/db.rs

@@ -0,0 +1,113 @@
+use std::{path::Path, fs};
+
+pub(crate) use serai_db::{Get, DbTxn, Db as DbTrait};
+use serai_db::{create_db, db_channel};
+
+use serai_client::{
+  primitives::NetworkId,
+  validator_sets::primitives::{Session, ValidatorSet},
+};
+
+use serai_cosign::SignedCosign;
+use serai_coordinator_substrate::NewSetInformation;
+use serai_coordinator_tributary::Transaction;
+
+#[cfg(all(feature = "parity-db", not(feature = "rocksdb")))]
+pub(crate) type Db = serai_db::ParityDb;
+#[cfg(feature = "rocksdb")]
+pub(crate) type Db = serai_db::RocksDB;
+
+#[allow(unused_variables, unreachable_code)]
+fn db(path: &str) -> Db {
+  {
+    let path: &Path = path.as_ref();
+    // This may error if this path already exists, which we shouldn't propagate/panic on. If this
+    // is a problem (such as we don't have the necessary permissions to write to this path), we
+    // expect the following DB opening to error.
+    let _: Result<_, _> = fs::create_dir_all(path.parent().unwrap());
+  }
+
+  #[cfg(all(feature = "parity-db", feature = "rocksdb"))]
+  panic!("built with parity-db and rocksdb");
+  #[cfg(all(feature = "parity-db", not(feature = "rocksdb")))]
+  let db = serai_db::new_parity_db(path);
+  #[cfg(feature = "rocksdb")]
+  let db = serai_db::new_rocksdb(path);
+  db
+}
+
+pub(crate) fn coordinator_db() -> Db {
+  let root_path = serai_env::var("DB_PATH").expect("path to DB wasn't specified");
+  db(&format!("{root_path}/coordinator/db"))
+}
+
+fn tributary_db_folder(set: ValidatorSet) -> String {
+  let root_path = serai_env::var("DB_PATH").expect("path to DB wasn't specified");
+  let network = match set.network {
+    NetworkId::Serai => panic!("creating Tributary for the Serai network"),
+    NetworkId::Bitcoin => "Bitcoin",
+    NetworkId::Ethereum => "Ethereum",
+    NetworkId::Monero => "Monero",
+  };
+  format!("{root_path}/tributary-{network}-{}", set.session.0)
+}
+
+pub(crate) fn tributary_db(set: ValidatorSet) -> Db {
+  db(&format!("{}/db", tributary_db_folder(set)))
+}
+
+pub(crate) fn prune_tributary_db(set: ValidatorSet) {
+  log::info!("pruning data directory for tributary {set:?}");
+  let db = tributary_db_folder(set);
+  if fs::exists(&db).expect("couldn't check if tributary DB exists") {
+    fs::remove_dir_all(db).unwrap();
+  }
+}
+
+create_db! {
+  Coordinator {
+    // The currently active Tributaries
+    ActiveTributaries: () -> Vec<NewSetInformation>,
+    // The latest Tributary to have been retired for a network
+    // Since Tributaries are retired sequentially, this is informative to if any Tributary has been
+    // retired
+    RetiredTributary: (network: NetworkId) -> Session,
+    // The last handled message from a Processor
+    LastProcessorMessage: (network: NetworkId) -> u64,
+    // Cosigns we produced and tried to intake yet incurred an error while doing so
+    ErroneousCosigns: () -> Vec<SignedCosign>,
+  }
+}
+
+db_channel! {
+  Coordinator {
+    // Cosigns we produced
+    SignedCosigns: () -> SignedCosign,
+    // Tributaries to clean up upon reboot
+    TributaryCleanup: () -> ValidatorSet,
+  }
+}
+
+mod _internal_db {
+  use super::*;
+
+  db_channel! {
+    Coordinator {
+      // Tributary transactions to publish
+      TributaryTransactions: (set: ValidatorSet) -> Transaction,
+    }
+  }
+}
+
+pub(crate) struct TributaryTransactions;
+impl TributaryTransactions {
+  pub(crate) fn send(txn: &mut impl DbTxn, set: ValidatorSet, tx: &Transaction) {
+    // If this set has yet to be retired, send this transaction
+    if RetiredTributary::get(txn, set.network).map(|session| session.0) < Some(set.session.0) {
+      _internal_db::TributaryTransactions::send(txn, set, tx);
+    }
+  }
+  pub(crate) fn try_recv(txn: &mut impl DbTxn, set: ValidatorSet) -> Option<Transaction> {
+    _internal_db::TributaryTransactions::try_recv(txn, set)
+  }
+}

coordinator/src/main.rs

@@ -1,6 +1,430 @@
-mod tributary;
-mod p2p;
+use core::{ops::Deref, time::Duration};
+use std::{sync::Arc, collections::HashMap, time::Instant};
 
-fn main() {
-  todo!("TODO")
+use zeroize::{Zeroize, Zeroizing};
+use rand_core::{RngCore, OsRng};
+
+use ciphersuite::{
+  group::{ff::PrimeField, GroupEncoding},
+  Ciphersuite, Ristretto,
+};
+
+use borsh::BorshDeserialize;
+
+use tokio::sync::mpsc;
+
+use serai_client::{
+  primitives::{NetworkId, PublicKey},
+  validator_sets::primitives::ValidatorSet,
+  Serai,
+};
+use message_queue::{Service, client::MessageQueue};
+
+use serai_task::{Task, TaskHandle, ContinuallyRan};
+
+use serai_cosign::{Faulted, SignedCosign, Cosigning};
+use serai_coordinator_substrate::{CanonicalEventStream, EphemeralEventStream, SignSlashReport};
+use serai_coordinator_tributary::{Signed, Transaction, SubstrateBlockPlans};
+
+mod db;
+use db::*;
+
+mod tributary;
+
+mod substrate;
+use substrate::SubstrateTask;
+
+mod p2p {
+  pub use serai_coordinator_p2p::*;
+  pub use serai_coordinator_libp2p_p2p::Libp2p;
+}
+
+// Use a zeroizing allocator for this entire application
+// While secrets should already be zeroized, the presence of secret keys in a networked application
+// (at increased risk of OOB reads) justifies the performance hit in case any secrets weren't
+// already
+#[global_allocator]
+static ALLOCATOR: zalloc::ZeroizingAlloc<std::alloc::System> =
+  zalloc::ZeroizingAlloc(std::alloc::System);
+
+async fn serai() -> Arc<Serai> {
+  const SERAI_CONNECTION_DELAY: Duration = Duration::from_secs(10);
+  const MAX_SERAI_CONNECTION_DELAY: Duration = Duration::from_secs(300);
+
+  let mut delay = SERAI_CONNECTION_DELAY;
+  loop {
+    let Ok(serai) = Serai::new(format!(
+      "http://{}:9944",
+      serai_env::var("SERAI_HOSTNAME").expect("Serai hostname wasn't provided")
+    ))
+    .await
+    else {
+      log::error!("couldn't connect to the Serai node");
+      tokio::time::sleep(delay).await;
+      delay = (delay + SERAI_CONNECTION_DELAY).min(MAX_SERAI_CONNECTION_DELAY);
+      continue;
+    };
+    log::info!("made initial connection to Serai node");
+    return Arc::new(serai);
+  }
+}
+
+fn spawn_cosigning<D: serai_db::Db>(
+  mut db: D,
+  serai: Arc<Serai>,
+  p2p: impl p2p::P2p,
+  tasks_to_run_upon_cosigning: Vec<TaskHandle>,
+  mut p2p_cosigns: mpsc::UnboundedReceiver<SignedCosign>,
+) {
+  let mut cosigning = Cosigning::spawn(db.clone(), serai, p2p.clone(), tasks_to_run_upon_cosigning);
+  tokio::spawn(async move {
+    const COSIGN_LOOP_INTERVAL: Duration = Duration::from_secs(5);
+
+    let last_cosign_rebroadcast = Instant::now();
+    loop {
+      // Intake our own cosigns
+      match Cosigning::<D>::latest_cosigned_block_number(&db) {
+        Ok(latest_cosigned_block_number) => {
+          let mut txn = db.txn();
+          // The cosigns we prior tried to intake yet failed to
+          let mut cosigns = ErroneousCosigns::get(&txn).unwrap_or(vec![]);
+          // The cosigns we have yet to intake
+          while let Some(cosign) = SignedCosigns::try_recv(&mut txn) {
+            cosigns.push(cosign);
+          }
+
+          let mut erroneous = vec![];
+          for cosign in cosigns {
+            // If this cosign is stale, move on
+            if cosign.cosign.block_number <= latest_cosigned_block_number {
+              continue;
+            }
+
+            match cosigning.intake_cosign(&cosign) {
+              // Publish this cosign
+              Ok(()) => p2p.publish_cosign(cosign).await,
+              Err(e) => {
+                assert!(e.temporal(), "signed an invalid cosign: {e:?}");
+                // Since this had a temporal error, queue it to try again later
+                erroneous.push(cosign);
+              }
+            };
+          }
+
+          // Save the cosigns with temporal errors to the database
+          ErroneousCosigns::set(&mut txn, &erroneous);
+
+          txn.commit();
+        }
+        Err(Faulted) => {
+          // We don't panic here as the following code rebroadcasts our cosigns which is
+          // necessary to inform other coordinators of the faulty cosigns
+          log::error!("cosigning faulted");
+        }
+      }
+
+      let time_till_cosign_rebroadcast = (last_cosign_rebroadcast +
+        serai_cosign::BROADCAST_FREQUENCY)
+        .saturating_duration_since(Instant::now());
+      tokio::select! {
+        () = tokio::time::sleep(time_till_cosign_rebroadcast) => {
+          for cosign in cosigning.cosigns_to_rebroadcast() {
+            p2p.publish_cosign(cosign).await;
+          }
+        }
+        cosign = p2p_cosigns.recv() => {
+          let cosign = cosign.expect("p2p cosigns channel was dropped?");
+          if cosigning.intake_cosign(&cosign).is_ok() {
+            p2p.publish_cosign(cosign).await;
+          }
+        }
+        // Make sure this loop runs at least this often
+        () = tokio::time::sleep(COSIGN_LOOP_INTERVAL) => {}
+      }
+    }
+  });
+}
+
+async fn handle_processor_messages(
+  mut db: impl serai_db::Db,
+  message_queue: Arc<MessageQueue>,
+  network: NetworkId,
+) {
+  loop {
+    let (msg_id, msg) = {
+      let msg = message_queue.next(Service::Processor(network)).await;
+      // Check this message's sender is as expected
+      assert_eq!(msg.from, Service::Processor(network));
+
+      // Check this message's ID is as expected
+      let last = LastProcessorMessage::get(&db, network);
+      let next = last.map(|id| id + 1).unwrap_or(0);
+      // This should either be the last message's ID, if we committed but didn't send our ACK, or
+      // the expected next message's ID
+      assert!((Some(msg.id) == last) || (msg.id == next));
+
+      // TODO: Check msg.sig
+
+      // If this is the message we already handled, and just failed to ACK, ACK it now and move on
+      if Some(msg.id) == last {
+        message_queue.ack(Service::Processor(network), msg.id).await;
+        continue;
+      }
+
+      (msg.id, messages::ProcessorMessage::deserialize(&mut msg.msg.as_slice()).unwrap())
+    };
+
+    let mut txn = db.txn();
+
+    match msg {
+      messages::ProcessorMessage::KeyGen(msg) => match msg {
+        messages::key_gen::ProcessorMessage::Participation { session, participation } => {
+          let set = ValidatorSet { network, session };
+          TributaryTransactions::send(
+            &mut txn,
+            set,
+            &Transaction::DkgParticipation { participation, signed: Signed::default() },
+          );
+        }
+        messages::key_gen::ProcessorMessage::GeneratedKeyPair {
+          session,
+          substrate_key,
+          network_key,
+        } => todo!("TODO Transaction::DkgConfirmationPreprocess"),
+        messages::key_gen::ProcessorMessage::Blame { session, participant } => {
+          let set = ValidatorSet { network, session };
+          TributaryTransactions::send(
+            &mut txn,
+            set,
+            &Transaction::RemoveParticipant {
+              participant: todo!("TODO"),
+              signed: Signed::default(),
+            },
+          );
+        }
+      },
+      messages::ProcessorMessage::Sign(msg) => match msg {
+        messages::sign::ProcessorMessage::InvalidParticipant { session, participant } => {
+          let set = ValidatorSet { network, session };
+          TributaryTransactions::send(
+            &mut txn,
+            set,
+            &Transaction::RemoveParticipant {
+              participant: todo!("TODO"),
+              signed: Signed::default(),
+            },
+          );
+        }
+        messages::sign::ProcessorMessage::Preprocesses { id, preprocesses } => {
+          todo!("TODO Transaction::Batch + Transaction::Sign")
+        }
+        messages::sign::ProcessorMessage::Shares { id, shares } => todo!("TODO Transaction::Sign"),
+      },
+      messages::ProcessorMessage::Coordinator(msg) => match msg {
+        messages::coordinator::ProcessorMessage::CosignedBlock { cosign } => {
+          SignedCosigns::send(&mut txn, &cosign);
+        }
+        messages::coordinator::ProcessorMessage::SignedBatch { batch } => {
+          todo!("TODO PublishBatchTask")
+        }
+        messages::coordinator::ProcessorMessage::SignedSlashReport { session, signature } => {
+          todo!("TODO PublishSlashReportTask")
+        }
+      },
+      messages::ProcessorMessage::Substrate(msg) => match msg {
+        messages::substrate::ProcessorMessage::SubstrateBlockAck { block, plans } => {
+          let mut by_session = HashMap::new();
+          for plan in plans {
+            by_session
+              .entry(plan.session)
+              .or_insert_with(|| Vec::with_capacity(1))
+              .push(plan.transaction_plan_id);
+          }
+          for (session, plans) in by_session {
+            let set = ValidatorSet { network, session };
+            SubstrateBlockPlans::set(&mut txn, set, block, &plans);
+            TributaryTransactions::send(
+              &mut txn,
+              set,
+              &Transaction::SubstrateBlock { hash: block },
+            );
+          }
+        }
+      },
+    }
+
+    // Mark this as the last handled message
+    LastProcessorMessage::set(&mut txn, network, &msg_id);
+    // Commit the txn
+    txn.commit();
+    // Now that we won't handle this message again, acknowledge it so we won't see it again
+    message_queue.ack(Service::Processor(network), msg_id).await;
+  }
+}
+
+#[tokio::main]
+async fn main() {
+  // Override the panic handler with one which will panic if any tokio task panics
+  {
+    let existing = std::panic::take_hook();
+    std::panic::set_hook(Box::new(move |panic| {
+      existing(panic);
+      const MSG: &str = "exiting the process due to a task panicking";
+      println!("{MSG}");
+      log::error!("{MSG}");
+      std::process::exit(1);
+    }));
+  }
+
+  // Initialize the logger
+  if std::env::var("RUST_LOG").is_err() {
+    std::env::set_var("RUST_LOG", serai_env::var("RUST_LOG").unwrap_or_else(|| "info".to_string()));
+  }
+  env_logger::init();
+  log::info!("starting coordinator service...");
+
+  // Read the Serai key from the env
+  let serai_key = {
+    let mut key_hex = serai_env::var("SERAI_KEY").expect("Serai key wasn't provided");
+    let mut key_vec = hex::decode(&key_hex).map_err(|_| ()).expect("Serai key wasn't hex-encoded");
+    key_hex.zeroize();
+    if key_vec.len() != 32 {
+      key_vec.zeroize();
+      panic!("Serai key had an invalid length");
+    }
+    let mut key_bytes = [0; 32];
+    key_bytes.copy_from_slice(&key_vec);
+    key_vec.zeroize();
+    let key = Zeroizing::new(<Ristretto as Ciphersuite>::F::from_repr(key_bytes).unwrap());
+    key_bytes.zeroize();
+    key
+  };
+
+  // Open the database
+  let mut db = coordinator_db();
+
+  let existing_tributaries_at_boot = {
+    let mut txn = db.txn();
+
+    // Cleanup all historic Tributaries
+    while let Some(to_cleanup) = TributaryCleanup::try_recv(&mut txn) {
+      prune_tributary_db(to_cleanup);
+      // Drain the cosign intents created for this set
+      while !Cosigning::<Db>::intended_cosigns(&mut txn, to_cleanup).is_empty() {}
+      // Drain the transactions to publish for this set
+      while TributaryTransactions::try_recv(&mut txn, to_cleanup).is_some() {}
+      // Remove the SignSlashReport notification
+      SignSlashReport::try_recv(&mut txn, to_cleanup);
+    }
+
+    // Remove retired Tributaries from ActiveTributaries
+    let mut active_tributaries = ActiveTributaries::get(&txn).unwrap_or(vec![]);
+    active_tributaries.retain(|tributary| {
+      RetiredTributary::get(&txn, tributary.set.network).map(|session| session.0) <
+        Some(tributary.set.session.0)
+    });
+    ActiveTributaries::set(&mut txn, &active_tributaries);
+
+    txn.commit();
+
+    active_tributaries
+  };
+
+  // Connect to the message-queue
+  let message_queue = Arc::new(MessageQueue::from_env(Service::Coordinator));
+
+  // Connect to the Serai node
+  let serai = serai().await;
+
+  let (p2p_add_tributary_send, p2p_add_tributary_recv) = mpsc::unbounded_channel();
+  let (p2p_retire_tributary_send, p2p_retire_tributary_recv) = mpsc::unbounded_channel();
+  let (p2p_cosigns_send, p2p_cosigns_recv) = mpsc::unbounded_channel();
+
+  // Spawn the P2P network
+  let p2p = {
+    let serai_keypair = {
+      let mut key_bytes = serai_key.to_bytes();
+      // Schnorrkel SecretKey is the key followed by 32 bytes of entropy for nonces
+      let mut expanded_key = Zeroizing::new([0; 64]);
+      expanded_key.as_mut_slice()[.. 32].copy_from_slice(&key_bytes);
+      OsRng.fill_bytes(&mut expanded_key.as_mut_slice()[32 ..]);
+      key_bytes.zeroize();
+      Zeroizing::new(
+        schnorrkel::SecretKey::from_bytes(expanded_key.as_slice()).unwrap().to_keypair(),
+      )
+    };
+    let p2p = p2p::Libp2p::new(&serai_keypair, serai.clone());
+    tokio::spawn(p2p::run::<Db, Transaction, _>(
+      db.clone(),
+      p2p.clone(),
+      p2p_add_tributary_recv,
+      p2p_retire_tributary_recv,
+      p2p_cosigns_send,
+    ));
+    p2p
+  };
+
+  // Spawn the Substrate scanners
+  let (substrate_task_def, substrate_task) = Task::new();
+  let (substrate_canonical_task_def, substrate_canonical_task) = Task::new();
+  tokio::spawn(
+    CanonicalEventStream::new(db.clone(), serai.clone())
+      .continually_run(substrate_canonical_task_def, vec![substrate_task.clone()]),
+  );
+  let (substrate_ephemeral_task_def, substrate_ephemeral_task) = Task::new();
+  tokio::spawn(
+    EphemeralEventStream::new(
+      db.clone(),
+      serai.clone(),
+      PublicKey::from_raw((<Ristretto as Ciphersuite>::generator() * serai_key.deref()).to_bytes()),
+    )
+    .continually_run(substrate_ephemeral_task_def, vec![substrate_task]),
+  );
+
+  // Spawn the cosign handler
+  spawn_cosigning(
+    db.clone(),
+    serai.clone(),
+    p2p.clone(),
+    // Run the Substrate scanners once we cosign new blocks
+    vec![substrate_canonical_task, substrate_ephemeral_task],
+    p2p_cosigns_recv,
+  );
+
+  // Spawn all Tributaries on-disk
+  for tributary in existing_tributaries_at_boot {
+    crate::tributary::spawn_tributary(
+      db.clone(),
+      message_queue.clone(),
+      p2p.clone(),
+      &p2p_add_tributary_send,
+      tributary,
+      serai_key.clone(),
+    )
+    .await;
+  }
+
+  // Handle the events from the Substrate scanner
+  tokio::spawn(
+    (SubstrateTask {
+      serai_key: serai_key.clone(),
+      db: db.clone(),
+      message_queue: message_queue.clone(),
+      p2p: p2p.clone(),
+      p2p_add_tributary: p2p_add_tributary_send.clone(),
+      p2p_retire_tributary: p2p_retire_tributary_send.clone(),
+    })
+    .continually_run(substrate_task_def, vec![]),
+  );
+
+  // Handle all of the Processors' messages
+  for network in serai_client::primitives::NETWORKS {
+    if network == NetworkId::Serai {
+      continue;
+    }
+    tokio::spawn(handle_processor_messages(db.clone(), message_queue.clone(), network));
+  }
+
+  // Run the spawned tasks ad-infinitum
+  core::future::pending().await
 }

coordinator/src/p2p/libp2p/mod.rs

@@ -1,214 +0,0 @@
-use core::{future::Future, time::Duration};
-use std::{
-  sync::Arc,
-  collections::{HashSet, HashMap},
-};
-
-use zeroize::Zeroizing;
-use schnorrkel::Keypair;
-
-use serai_client::{
-  primitives::{NetworkId, PublicKey},
-  validator_sets::primitives::ValidatorSet,
-  Serai,
-};
-
-use tokio::sync::{mpsc, oneshot, RwLock};
-
-use serai_task::{Task, ContinuallyRan};
-
-use libp2p::{
-  multihash::Multihash,
-  identity::{self, PeerId},
-  tcp::Config as TcpConfig,
-  yamux,
-  swarm::NetworkBehaviour,
-  SwarmBuilder,
-};
-
-use crate::p2p::TributaryBlockWithCommit;
-
-/// A struct to sync the validators from the Serai node in order to keep track of them.
-mod validators;
-use validators::UpdateValidatorsTask;
-
-/// The authentication protocol upgrade to limit the P2P network to active validators.
-mod authenticate;
-use authenticate::OnlyValidators;
-
-/// The dial task, to find new peers to connect to
-mod dial;
-use dial::DialTask;
-
-/// The request-response messages and behavior
-mod reqres;
-use reqres::{Request, Response};
-
-/// The gossip messages and behavior
-mod gossip;
-
-/// The swarm task, running it and dispatching to/from it
-mod swarm;
-use swarm::SwarmTask;
-
-const PORT: u16 = 30563; // 5132 ^ (('c' << 8) | 'o')
-
-// usize::max, manually implemented, as max isn't a const fn
-const MAX_LIBP2P_MESSAGE_SIZE: usize =
-  if gossip::MAX_LIBP2P_GOSSIP_MESSAGE_SIZE > reqres::MAX_LIBP2P_REQRES_MESSAGE_SIZE {
-    gossip::MAX_LIBP2P_GOSSIP_MESSAGE_SIZE
-  } else {
-    reqres::MAX_LIBP2P_REQRES_MESSAGE_SIZE
-  };
-
-fn peer_id_from_public(public: PublicKey) -> PeerId {
-  // 0 represents the identity Multihash, that no hash was performed
-  // It's an internal constant so we can't refer to the constant inside libp2p
-  PeerId::from_multihash(Multihash::wrap(0, &public.0).unwrap()).unwrap()
-}
-
-struct Peer<'a> {
-  outbound_requests: &'a mpsc::UnboundedSender<(PeerId, Request, oneshot::Sender<Response>)>,
-  id: PeerId,
-}
-impl crate::p2p::Peer<'_> for Peer<'_> {
-  fn send_heartbeat(
-    &self,
-    set: ValidatorSet,
-    latest_block_hash: [u8; 32],
-  ) -> impl Send + Future<Output = Option<Vec<TributaryBlockWithCommit>>> {
-    const HEARBEAT_TIMEOUT: Duration = Duration::from_secs(5);
-    async move {
-      let request = Request::Heartbeat { set, latest_block_hash };
-      let (sender, receiver) = oneshot::channel();
-      self
-        .outbound_requests
-        .send((self.id, request, sender))
-        .expect("outbound requests recv channel was dropped?");
-      match tokio::time::timeout(HEARBEAT_TIMEOUT, receiver).await.ok()?.ok()? {
-        Response::None => Some(vec![]),
-        Response::Blocks(blocks) => Some(blocks),
-        // TODO: Disconnect this peer
-        Response::NotableCosigns(_) => None,
-      }
-    }
-  }
-}
-
-#[derive(Clone)]
-struct Peers {
-  peers: Arc<RwLock<HashMap<NetworkId, HashSet<PeerId>>>>,
-}
-
-#[derive(NetworkBehaviour)]
-struct Behavior {
-  reqres: reqres::Behavior,
-  gossip: gossip::Behavior,
-}
-
-#[derive(Clone)]
-struct Libp2p {
-  peers: Peers,
-  outbound_requests: mpsc::UnboundedSender<(PeerId, Request, oneshot::Sender<Response>)>,
-}
-
-impl Libp2p {
-  pub(crate) fn new(serai_key: &Zeroizing<Keypair>, serai: Serai) -> Libp2p {
-    // Define the object we track peers with
-    let peers = Peers { peers: Arc::new(RwLock::new(HashMap::new())) };
-
-    // Define the dial task
-    let (dial_task_def, dial_task) = Task::new();
-    let (to_dial_send, to_dial_recv) = mpsc::unbounded_channel();
-    tokio::spawn(
-      DialTask::new(serai.clone(), peers.clone(), to_dial_send)
-        .continually_run(dial_task_def, vec![]),
-    );
-
-    // Define the Validators object used for validating new connections
-    let connection_validators = UpdateValidatorsTask::spawn(serai.clone());
-    let new_only_validators = |noise_keypair: &identity::Keypair| -> Result<_, ()> {
-      Ok(OnlyValidators {
-        serai_key: serai_key.clone(),
-        validators: connection_validators.clone(),
-        noise_keypair: noise_keypair.clone(),
-      })
-    };
-
-    let new_yamux = || {
-      let mut config = yamux::Config::default();
-      // 1 MiB default + max message size
-      config.set_max_buffer_size((1024 * 1024) + MAX_LIBP2P_MESSAGE_SIZE);
-      // 256 KiB default + max message size
-      config.set_receive_window_size(((256 * 1024) + MAX_LIBP2P_MESSAGE_SIZE).try_into().unwrap());
-      config
-    };
-
-    let behavior = Behavior { reqres: reqres::new_behavior(), gossip: gossip::new_behavior() };
-
-    let mut swarm = SwarmBuilder::with_existing_identity(identity::Keypair::generate_ed25519())
-      .with_tokio()
-      .with_tcp(TcpConfig::default().nodelay(false), new_only_validators, new_yamux)
-      .unwrap()
-      .with_behaviour(|_| behavior)
-      .unwrap()
-      .build();
-    swarm.listen_on(format!("/ip4/0.0.0.0/tcp/{PORT}").parse().unwrap()).unwrap();
-    swarm.listen_on(format!("/ip6/::/tcp/{PORT}").parse().unwrap()).unwrap();
-
-    let swarm_validators = UpdateValidatorsTask::spawn(serai);
-
-    let (gossip_send, gossip_recv) = mpsc::unbounded_channel();
-    let (signed_cosigns_send, signed_cosigns_recv) = mpsc::unbounded_channel();
-    let (tributary_gossip_send, tributary_gossip_recv) = mpsc::unbounded_channel();
-
-    let (outbound_requests_send, outbound_requests_recv) = mpsc::unbounded_channel();
-
-    let (heartbeat_requests_send, heartbeat_requests_recv) = mpsc::unbounded_channel();
-    let (notable_cosign_requests_send, notable_cosign_requests_recv) = mpsc::unbounded_channel();
-    let (inbound_request_responses_send, inbound_request_responses_recv) =
-      mpsc::unbounded_channel();
-
-    // Create the swarm task
-    SwarmTask::spawn(
-      dial_task,
-      to_dial_recv,
-      swarm_validators,
-      peers,
-      swarm,
-      gossip_recv,
-      signed_cosigns_send,
-      tributary_gossip_send,
-      outbound_requests_recv,
-      heartbeat_requests_send,
-      notable_cosign_requests_send,
-      inbound_request_responses_recv,
-    );
-
-    // gossip_send, signed_cosigns_recv, tributary_gossip_recv, outbound_requests_send,
-    // heartbeat_requests_recv, notable_cosign_requests_recv, inbound_request_responses_send
-    todo!("TODO");
-  }
-}
-
-impl tributary::P2p for Libp2p {
-  fn broadcast(&self, genesis: [u8; 32], msg: Vec<u8>) -> impl Send + Future<Output = ()> {
-    async move { todo!("TODO") }
-  }
-}
-
-impl crate::p2p::P2p for Libp2p {
-  type Peer<'a> = Peer<'a>;
-  fn peers(&self, network: NetworkId) -> impl Send + Future<Output = Vec<Self::Peer<'_>>> {
-    async move {
-      let Some(peer_ids) = self.peers.peers.read().await.get(&network).cloned() else {
-        return vec![];
-      };
-      let mut res = vec![];
-      for id in peer_ids {
-        res.push(Peer { outbound_requests: &self.outbound_requests, id });
-      }
-      res
-    }
-  }
-}

coordinator/src/p2p/mod.rs

@@ -1,31 +0,0 @@
-use core::future::Future;
-
-use borsh::{BorshSerialize, BorshDeserialize};
-
-use serai_client::{primitives::NetworkId, validator_sets::primitives::ValidatorSet};
-
-/// The libp2p-backed P2p network
-mod libp2p;
-
-/// The heartbeat task, effecting sync of Tributaries
-mod heartbeat;
-
-/// A tributary block and its commit.
-#[derive(Clone, BorshSerialize, BorshDeserialize)]
-pub(crate) struct TributaryBlockWithCommit {
-  pub(crate) block: Vec<u8>,
-  pub(crate) commit: Vec<u8>,
-}
-
-trait Peer<'a>: Send {
-  fn send_heartbeat(
-    &self,
-    set: ValidatorSet,
-    latest_block_hash: [u8; 32],
-  ) -> impl Send + Future<Output = Option<Vec<TributaryBlockWithCommit>>>;
-}
-
-trait P2p: Send + Sync + tributary::P2p {
-  type Peer<'a>: Peer<'a>;
-  fn peers(&self, network: NetworkId) -> impl Send + Future<Output = Vec<Self::Peer<'_>>>;
-}

coordinator/src/substrate.rs

@@ -0,0 +1,159 @@
+use core::future::Future;
+use std::sync::Arc;
+
+use zeroize::Zeroizing;
+
+use ciphersuite::{Ciphersuite, Ristretto};
+
+use tokio::sync::mpsc;
+
+use serai_db::{DbTxn, Db as DbTrait};
+
+use serai_client::validator_sets::primitives::{Session, ValidatorSet};
+use message_queue::{Service, Metadata, client::MessageQueue};
+
+use tributary_sdk::Tributary;
+
+use serai_task::ContinuallyRan;
+
+use serai_coordinator_tributary::Transaction;
+use serai_coordinator_p2p::P2p;
+
+use crate::Db;
+
+pub(crate) struct SubstrateTask<P: P2p> {
+  pub(crate) serai_key: Zeroizing<<Ristretto as Ciphersuite>::F>,
+  pub(crate) db: Db,
+  pub(crate) message_queue: Arc<MessageQueue>,
+  pub(crate) p2p: P,
+  pub(crate) p2p_add_tributary:
+    mpsc::UnboundedSender<(ValidatorSet, Tributary<Db, Transaction, P>)>,
+  pub(crate) p2p_retire_tributary: mpsc::UnboundedSender<ValidatorSet>,
+}
+
+impl<P: P2p> ContinuallyRan for SubstrateTask<P> {
+  type Error = String; // TODO
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
+    async move {
+      let mut made_progress = false;
+
+      // Handle the Canonical events
+      for network in serai_client::primitives::NETWORKS {
+        loop {
+          let mut txn = self.db.txn();
+          let Some(msg) = serai_coordinator_substrate::Canonical::try_recv(&mut txn, network)
+          else {
+            break;
+          };
+
+          match msg {
+            // TODO: Stop trying to confirm the DKG
+            messages::substrate::CoordinatorMessage::SetKeys { .. } => todo!("TODO"),
+            messages::substrate::CoordinatorMessage::SlashesReported { session } => {
+              let prior_retired = crate::db::RetiredTributary::get(&txn, network);
+              let next_to_be_retired =
+                prior_retired.map(|session| Session(session.0 + 1)).unwrap_or(Session(0));
+              assert_eq!(session, next_to_be_retired);
+              crate::db::RetiredTributary::set(&mut txn, network, &session);
+              self
+                .p2p_retire_tributary
+                .send(ValidatorSet { network, session })
+                .expect("p2p retire_tributary channel dropped?");
+            }
+            messages::substrate::CoordinatorMessage::Block { .. } => {}
+          }
+
+          let msg = messages::CoordinatorMessage::from(msg);
+          let metadata = Metadata {
+            from: Service::Coordinator,
+            to: Service::Processor(network),
+            intent: msg.intent(),
+          };
+          let msg = borsh::to_vec(&msg).unwrap();
+          self.message_queue.queue(metadata, msg).await?;
+          txn.commit();
+          made_progress = true;
+        }
+      }
+
+      // Handle the NewSet events
+      loop {
+        let mut txn = self.db.txn();
+        let Some(new_set) = serai_coordinator_substrate::NewSet::try_recv(&mut txn) else { break };
+
+        if let Some(historic_session) = new_set.set.session.0.checked_sub(2) {
+          // We should have retired this session if we're here
+          if crate::db::RetiredTributary::get(&txn, new_set.set.network).map(|session| session.0) <
+            Some(historic_session)
+          {
+            /*
+              If we haven't, it's because we're processing the NewSet event before the retiry
+              event from the Canonical event stream. This happens if the Canonical event, and
+              then the NewSet event, is fired while we're already iterating over NewSet events.
+
+              We break, dropping the txn, restoring this NewSet to the database, so we'll only
+              handle it once a future iteration of this loop handles the retiry event.
+            */
+            break;
+          }
+
+          /*
+            Queue this historical Tributary for deletion.
+
+            We explicitly don't queue this upon Tributary retire, instead here, to give time to
+            investigate retired Tributaries if questions are raised post-retiry. This gives a
+            week (the duration of the following session) after the Tributary has been retired to
+            make a backup of the data directory for any investigations.
+          */
+          crate::db::TributaryCleanup::send(
+            &mut txn,
+            &ValidatorSet { network: new_set.set.network, session: Session(historic_session) },
+          );
+        }
+
+        // Save this Tributary as active to the database
+        {
+          let mut active_tributaries =
+            crate::db::ActiveTributaries::get(&txn).unwrap_or(Vec::with_capacity(1));
+          active_tributaries.push(new_set.clone());
+          crate::db::ActiveTributaries::set(&mut txn, &active_tributaries);
+        }
+
+        // Send GenerateKey to the processor
+        let msg = messages::key_gen::CoordinatorMessage::GenerateKey {
+          session: new_set.set.session,
+          threshold: new_set.threshold,
+          evrf_public_keys: new_set.evrf_public_keys.clone(),
+        };
+        let msg = messages::CoordinatorMessage::from(msg);
+        let metadata = Metadata {
+          from: Service::Coordinator,
+          to: Service::Processor(new_set.set.network),
+          intent: msg.intent(),
+        };
+        let msg = borsh::to_vec(&msg).unwrap();
+        self.message_queue.queue(metadata, msg).await?;
+
+        // Commit the transaction for all of this
+        txn.commit();
+
+        // Now spawn the Tributary
+        // If we reboot after committing the txn, but before this is called, this will be called
+        // on boot
+        crate::tributary::spawn_tributary(
+          self.db.clone(),
+          self.message_queue.clone(),
+          self.p2p.clone(),
+          &self.p2p_add_tributary,
+          new_set,
+          self.serai_key.clone(),
+        )
+        .await;
+
+        made_progress = true;
+      }
+
+      Ok(made_progress)
+    }
+  }
+}

coordinator/src/tributary.rs

@@ -0,0 +1,453 @@
+use core::{future::Future, time::Duration};
+use std::sync::Arc;
+
+use zeroize::Zeroizing;
+use rand_core::OsRng;
+use blake2::{digest::typenum::U32, Digest, Blake2s};
+use ciphersuite::{Ciphersuite, Ristretto};
+
+use tokio::sync::mpsc;
+
+use serai_db::{Get, DbTxn, Db as DbTrait, create_db, db_channel};
+
+use scale::Encode;
+use serai_client::validator_sets::primitives::ValidatorSet;
+
+use tributary_sdk::{TransactionKind, TransactionError, ProvidedError, TransactionTrait, Tributary};
+
+use serai_task::{Task, TaskHandle, DoesNotError, ContinuallyRan};
+
+use message_queue::{Service, Metadata, client::MessageQueue};
+
+use serai_cosign::{Faulted, CosignIntent, Cosigning};
+use serai_coordinator_substrate::{NewSetInformation, SignSlashReport};
+use serai_coordinator_tributary::{Transaction, ProcessorMessages, CosignIntents, ScanTributaryTask};
+use serai_coordinator_p2p::P2p;
+
+use crate::{Db, TributaryTransactions};
+
+db_channel! {
+  Coordinator {
+    PendingCosigns: (set: ValidatorSet) -> CosignIntent,
+  }
+}
+
+/// Provide a Provided Transaction to the Tributary.
+///
+/// This is not a well-designed function. This is specific to the context in which its called,
+/// within this file. It should only be considered an internal helper for this domain alone.
+async fn provide_transaction<TD: DbTrait, P: P2p>(
+  set: ValidatorSet,
+  tributary: &Tributary<TD, Transaction, P>,
+  tx: Transaction,
+) {
+  match tributary.provide_transaction(tx.clone()).await {
+    // The Tributary uses its own DB, so we may provide this multiple times if we reboot before
+    // committing the txn which provoked this
+    Ok(()) | Err(ProvidedError::AlreadyProvided) => {}
+    Err(ProvidedError::NotProvided) => {
+      panic!("providing a Transaction which wasn't a Provided transaction: {tx:?}");
+    }
+    Err(ProvidedError::InvalidProvided(e)) => {
+      panic!("providing an invalid Provided transaction, tx: {tx:?}, error: {e:?}")
+    }
+    // The Tributary's scan task won't advance if we don't have the Provided transactions
+    // present on-chain, and this enters an infinite loop to block the calling task from
+    // advancing
+    Err(ProvidedError::LocalMismatchesOnChain) => loop {
+      log::error!(
+        "Tributary {:?} was supposed to provide {:?} but peers disagree, halting Tributary",
+        set,
+        tx,
+      );
+      // Print this every five minutes as this does need to be handled
+      tokio::time::sleep(Duration::from_secs(5 * 60)).await;
+    },
+  }
+}
+
+/// Provides Cosign/Cosigned Transactions onto the Tributary.
+pub(crate) struct ProvideCosignCosignedTransactionsTask<CD: DbTrait, TD: DbTrait, P: P2p> {
+  db: CD,
+  tributary_db: TD,
+  set: NewSetInformation,
+  tributary: Tributary<TD, Transaction, P>,
+}
+impl<CD: DbTrait, TD: DbTrait, P: P2p> ContinuallyRan
+  for ProvideCosignCosignedTransactionsTask<CD, TD, P>
+{
+  type Error = String;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
+    async move {
+      let mut made_progress = false;
+
+      // Check if we produced any cosigns we were supposed to
+      let mut pending_notable_cosign = false;
+      loop {
+        let mut txn = self.db.txn();
+
+        // Fetch the next cosign this tributary should handle
+        let Some(cosign) = PendingCosigns::try_recv(&mut txn, self.set.set) else { break };
+        pending_notable_cosign = cosign.notable;
+
+        // If we (Serai) haven't cosigned this block, break as this is still pending
+        let latest = match Cosigning::<CD>::latest_cosigned_block_number(&txn) {
+          Ok(latest) => latest,
+          Err(Faulted) => {
+            log::error!("cosigning faulted");
+            Err("cosigning faulted")?
+          }
+        };
+        if latest < cosign.block_number {
+          break;
+        }
+
+        // Because we've cosigned it, provide the TX for that
+        {
+          let mut txn = self.tributary_db.txn();
+          CosignIntents::provide(&mut txn, self.set.set, &cosign);
+          txn.commit();
+        }
+        provide_transaction(
+          self.set.set,
+          &self.tributary,
+          Transaction::Cosigned { substrate_block_hash: cosign.block_hash },
+        )
+        .await;
+        // Clear pending_notable_cosign since this cosign isn't pending
+        pending_notable_cosign = false;
+
+        // Commit the txn to clear this from PendingCosigns
+        txn.commit();
+        made_progress = true;
+      }
+
+      // If we don't have any notable cosigns pending, provide the next set of cosign intents
+      if !pending_notable_cosign {
+        let mut txn = self.db.txn();
+        // intended_cosigns will only yield up to and including the next notable cosign
+        for cosign in Cosigning::<CD>::intended_cosigns(&mut txn, self.set.set) {
+          // Flag this cosign as pending
+          PendingCosigns::send(&mut txn, self.set.set, &cosign);
+          // Provide the transaction to queue it for work
+          provide_transaction(
+            self.set.set,
+            &self.tributary,
+            Transaction::Cosign { substrate_block_hash: cosign.block_hash },
+          )
+          .await;
+        }
+        txn.commit();
+        made_progress = true;
+      }
+
+      Ok(made_progress)
+    }
+  }
+}
+
+/// Adds all of the transactions sent via `TributaryTransactions`.
+pub(crate) struct AddTributaryTransactionsTask<CD: DbTrait, TD: DbTrait, P: P2p> {
+  db: CD,
+  tributary_db: TD,
+  tributary: Tributary<TD, Transaction, P>,
+  set: ValidatorSet,
+  key: Zeroizing<<Ristretto as Ciphersuite>::F>,
+}
+impl<CD: DbTrait, TD: DbTrait, P: P2p> ContinuallyRan for AddTributaryTransactionsTask<CD, TD, P> {
+  type Error = DoesNotError;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
+    async move {
+      let mut made_progress = false;
+      loop {
+        let mut txn = self.db.txn();
+        let Some(mut tx) = TributaryTransactions::try_recv(&mut txn, self.set) else { break };
+
+        let kind = tx.kind();
+        match kind {
+          TransactionKind::Provided(_) => provide_transaction(self.set, &self.tributary, tx).await,
+          TransactionKind::Unsigned | TransactionKind::Signed(_, _) => {
+            // If this is a signed transaction, sign it
+            if matches!(kind, TransactionKind::Signed(_, _)) {
+              tx.sign(&mut OsRng, self.tributary.genesis(), &self.key);
+            }
+
+            // Actually add the transaction
+            // TODO: If this is a preprocess, make sure the topic has been recognized
+            let res = self.tributary.add_transaction(tx.clone()).await;
+            match &res {
+              // Fresh publication, already published
+              Ok(true | false) => {}
+              Err(
+                TransactionError::TooLargeTransaction |
+                TransactionError::InvalidSigner |
+                TransactionError::InvalidNonce |
+                TransactionError::InvalidSignature |
+                TransactionError::InvalidContent,
+              ) => {
+                panic!("created an invalid transaction, tx: {tx:?}, err: {res:?}");
+              }
+              // We've published too many transactions recently
+              // Drop this txn to try to publish it again later on a future iteration
+              Err(TransactionError::TooManyInMempool) => {
+                drop(txn);
+                break;
+              }
+              // This isn't a Provided transaction so this should never be hit
+              Err(TransactionError::ProvidedAddedToMempool) => unreachable!(),
+            }
+          }
+        }
+
+        made_progress = true;
+        txn.commit();
+      }
+      Ok(made_progress)
+    }
+  }
+}
+
+/// Takes the messages from ScanTributaryTask and publishes them to the message-queue.
+pub(crate) struct TributaryProcessorMessagesTask<TD: DbTrait> {
+  tributary_db: TD,
+  set: ValidatorSet,
+  message_queue: Arc<MessageQueue>,
+}
+impl<TD: DbTrait> ContinuallyRan for TributaryProcessorMessagesTask<TD> {
+  type Error = String; // TODO
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
+    async move {
+      let mut made_progress = false;
+      loop {
+        let mut txn = self.tributary_db.txn();
+        let Some(msg) = ProcessorMessages::try_recv(&mut txn, self.set) else { break };
+        let metadata = Metadata {
+          from: Service::Coordinator,
+          to: Service::Processor(self.set.network),
+          intent: msg.intent(),
+        };
+        let msg = borsh::to_vec(&msg).unwrap();
+        self.message_queue.queue(metadata, msg).await?;
+        txn.commit();
+        made_progress = true;
+      }
+      Ok(made_progress)
+    }
+  }
+}
+
+/// Checks for the notification to sign a slash report and does so if present.
+pub(crate) struct SignSlashReportTask<CD: DbTrait, TD: DbTrait, P: P2p> {
+  db: CD,
+  tributary_db: TD,
+  tributary: Tributary<TD, Transaction, P>,
+  set: NewSetInformation,
+  key: Zeroizing<<Ristretto as Ciphersuite>::F>,
+}
+impl<CD: DbTrait, TD: DbTrait, P: P2p> ContinuallyRan for SignSlashReportTask<CD, TD, P> {
+  type Error = DoesNotError;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
+    async move {
+      let mut txn = self.db.txn();
+      let Some(()) = SignSlashReport::try_recv(&mut txn, self.set.set) else { return Ok(false) };
+
+      // Fetch the slash report for this Tributary
+      let mut tx =
+        serai_coordinator_tributary::slash_report_transaction(&self.tributary_db, &self.set);
+      tx.sign(&mut OsRng, self.tributary.genesis(), &self.key);
+
+      let res = self.tributary.add_transaction(tx.clone()).await;
+      match &res {
+        // Fresh publication, already published
+        Ok(true | false) => {}
+        Err(
+          TransactionError::TooLargeTransaction |
+          TransactionError::InvalidSigner |
+          TransactionError::InvalidNonce |
+          TransactionError::InvalidSignature |
+          TransactionError::InvalidContent,
+        ) => {
+          panic!("created an invalid SlashReport transaction, tx: {tx:?}, err: {res:?}");
+        }
+        // We've published too many transactions recently
+        // Drop this txn to try to publish it again later on a future iteration
+        Err(TransactionError::TooManyInMempool) => {
+          drop(txn);
+          return Ok(false);
+        }
+        // This isn't a Provided transaction so this should never be hit
+        Err(TransactionError::ProvidedAddedToMempool) => unreachable!(),
+      }
+
+      txn.commit();
+      Ok(true)
+    }
+  }
+}
+
+/// Run the scan task whenever the Tributary adds a new block.
+async fn scan_on_new_block<CD: DbTrait, TD: DbTrait, P: P2p>(
+  db: CD,
+  set: ValidatorSet,
+  tributary: Tributary<TD, Transaction, P>,
+  scan_tributary_task: TaskHandle,
+  tasks_to_keep_alive: Vec<TaskHandle>,
+) {
+  loop {
+    // Break once this Tributary is retired
+    if crate::RetiredTributary::get(&db, set.network).map(|session| session.0) >=
+      Some(set.session.0)
+    {
+      drop(tasks_to_keep_alive);
+      break;
+    }
+
+    // Have the tributary scanner run as soon as there's a new block
+    match tributary.next_block_notification().await.await {
+      Ok(()) => scan_tributary_task.run_now(),
+      // unreachable since this owns the tributary object and doesn't drop it
+      Err(_) => panic!("tributary was dropped causing notification to error"),
+    }
+  }
+}
+
+/// Spawn a Tributary.
+///
+/// This will:
+/// - Spawn the Tributary
+/// - Inform the P2P network of the Tributary
+/// - Spawn the ScanTributaryTask
+/// - Spawn the ProvideCosignCosignedTransactionsTask
+/// - Spawn the TributaryProcessorMessagesTask
+/// - Spawn the SignSlashReportTask
+/// - Iterate the scan task whenever a new block occurs (not just on the standard interval)
+pub(crate) async fn spawn_tributary<P: P2p>(
+  db: Db,
+  message_queue: Arc<MessageQueue>,
+  p2p: P,
+  p2p_add_tributary: &mpsc::UnboundedSender<(ValidatorSet, Tributary<Db, Transaction, P>)>,
+  set: NewSetInformation,
+  serai_key: Zeroizing<<Ristretto as Ciphersuite>::F>,
+) {
+  // Don't spawn retired Tributaries
+  if crate::db::RetiredTributary::get(&db, set.set.network).map(|session| session.0) >=
+    Some(set.set.session.0)
+  {
+    return;
+  }
+
+  let genesis = <[u8; 32]>::from(Blake2s::<U32>::digest((set.serai_block, set.set).encode()));
+
+  // Since the Serai block will be finalized, then cosigned, before we handle this, this time will
+  // be a couple of minutes stale. While the Tributary will still function with a start time in the
+  // past, the Tributary will immediately incur round timeouts. We reduce these by adding a
+  // constant delay of a couple of minutes.
+  const TRIBUTARY_START_TIME_DELAY: u64 = 120;
+  let start_time = set.declaration_time + TRIBUTARY_START_TIME_DELAY;
+
+  let mut tributary_validators = Vec::with_capacity(set.validators.len());
+  for (validator, weight) in set.validators.iter().copied() {
+    let validator_key = <Ristretto as Ciphersuite>::read_G(&mut validator.0.as_slice())
+      .expect("Serai validator had an invalid public key");
+    let weight = u64::from(weight);
+    tributary_validators.push((validator_key, weight));
+  }
+
+  // Spawn the Tributary
+  let tributary_db = crate::db::tributary_db(set.set);
+  let tributary = Tributary::new(
+    tributary_db.clone(),
+    genesis,
+    start_time,
+    serai_key.clone(),
+    tributary_validators,
+    p2p,
+  )
+  .await
+  .unwrap();
+  let reader = tributary.reader();
+
+  // Inform the P2P network
+  p2p_add_tributary
+    .send((set.set, tributary.clone()))
+    .expect("p2p's add_tributary channel was closed?");
+
+  // Spawn the task to provide Cosign/Cosigned transactions onto the Tributary
+  let (provide_cosign_cosigned_transactions_task_def, provide_cosign_cosigned_transactions_task) =
+    Task::new();
+  tokio::spawn(
+    (ProvideCosignCosignedTransactionsTask {
+      db: db.clone(),
+      tributary_db: tributary_db.clone(),
+      set: set.clone(),
+      tributary: tributary.clone(),
+    })
+    .continually_run(provide_cosign_cosigned_transactions_task_def, vec![]),
+  );
+
+  // Spawn the task to send all messages from the Tributary scanner to the message-queue
+  let (scan_tributary_messages_task_def, scan_tributary_messages_task) = Task::new();
+  tokio::spawn(
+    (TributaryProcessorMessagesTask {
+      tributary_db: tributary_db.clone(),
+      set: set.set,
+      message_queue,
+    })
+    .continually_run(scan_tributary_messages_task_def, vec![]),
+  );
+
+  // Spawn the scan task
+  let (scan_tributary_task_def, scan_tributary_task) = Task::new();
+  tokio::spawn(
+    ScanTributaryTask::<_, P>::new(tributary_db.clone(), &set, reader)
+      // This is the only handle for this TributaryProcessorMessagesTask, so when this task is
+      // dropped, it will be too
+      .continually_run(scan_tributary_task_def, vec![scan_tributary_messages_task]),
+  );
+
+  // Spawn the sign slash report task
+  let (sign_slash_report_task_def, sign_slash_report_task) = Task::new();
+  tokio::spawn(
+    (SignSlashReportTask {
+      db: db.clone(),
+      tributary_db: tributary_db.clone(),
+      tributary: tributary.clone(),
+      set: set.clone(),
+      key: serai_key.clone(),
+    })
+    .continually_run(sign_slash_report_task_def, vec![]),
+  );
+
+  // Spawn the add transactions task
+  let (add_tributary_transactions_task_def, add_tributary_transactions_task) = Task::new();
+  tokio::spawn(
+    (AddTributaryTransactionsTask {
+      db: db.clone(),
+      tributary_db,
+      tributary: tributary.clone(),
+      set: set.set,
+      key: serai_key,
+    })
+    .continually_run(add_tributary_transactions_task_def, vec![]),
+  );
+
+  // Whenever a new block occurs, immediately run the scan task
+  // This function also preserves the ProvideCosignCosignedTransactionsTask handle until the
+  // Tributary is retired, ensuring it isn't dropped prematurely and that the task don't run ad
+  // infinitum
+  tokio::spawn(scan_on_new_block(
+    db,
+    set.set,
+    tributary,
+    scan_tributary_task,
+    vec![
+      provide_cosign_cosigned_transactions_task,
+      sign_slash_report_task,
+      add_tributary_transactions_task,
+    ],
+  ));
+}

coordinator/src/tributary/mod.rs

@@ -1,6 +0,0 @@
-mod transaction;
-pub use transaction::Transaction;
-
-mod db;
-
-mod scan;

coordinator/src/tributary/scan.rs

@@ -1,408 +0,0 @@
-use core::future::Future;
-use std::collections::HashMap;
-
-use ciphersuite::group::GroupEncoding;
-
-use serai_client::{
-  primitives::SeraiAddress,
-  validator_sets::primitives::{ValidatorSet, Slash},
-};
-
-use tributary::{
-  Signed as TributarySigned, TransactionKind, TransactionTrait,
-  Transaction as TributaryTransaction, Block, TributaryReader,
-  tendermint::{
-    tx::{TendermintTx, Evidence, decode_signed_message},
-    TendermintNetwork,
-  },
-};
-
-use serai_db::*;
-use serai_task::ContinuallyRan;
-
-use messages::sign::VariantSignId;
-
-use crate::tributary::{
-  db::*,
-  transaction::{SigningProtocolRound, Signed, Transaction},
-};
-
-struct ScanBlock<'a, D: DbTxn, TD: Db> {
-  txn: &'a mut D,
-  set: ValidatorSet,
-  validators: &'a [SeraiAddress],
-  total_weight: u64,
-  validator_weights: &'a HashMap<SeraiAddress, u64>,
-  tributary: &'a TributaryReader<TD, Transaction>,
-}
-impl<'a, D: DbTxn, TD: Db> ScanBlock<'a, D, TD> {
-  fn potentially_start_cosign(&mut self) {
-    // Don't start a new cosigning instance if we're actively running one
-    if TributaryDb::actively_cosigning(self.txn, self.set) {
-      return;
-    }
-
-    // Start cosigning the latest intended-to-be-cosigned block
-    let Some(latest_substrate_block_to_cosign) =
-      TributaryDb::latest_substrate_block_to_cosign(self.txn, self.set)
-    else {
-      return;
-    };
-
-    let substrate_block_number = todo!("TODO");
-
-    // Mark us as actively cosigning
-    TributaryDb::start_cosigning(self.txn, self.set, substrate_block_number);
-    // Send the message for the processor to start signing
-    TributaryDb::send_message(
-      self.txn,
-      self.set,
-      messages::coordinator::CoordinatorMessage::CosignSubstrateBlock {
-        session: self.set.session,
-        block_number: substrate_block_number,
-        block: latest_substrate_block_to_cosign,
-      },
-    );
-  }
-  fn handle_application_tx(&mut self, block_number: u64, tx: Transaction) {
-    let signer = |signed: Signed| SeraiAddress(signed.signer.to_bytes());
-
-    if let TransactionKind::Signed(_, TributarySigned { signer, .. }) = tx.kind() {
-      // Don't handle transactions from those fatally slashed
-      // TODO: The fact they can publish these TXs makes this a notable spam vector
-      if TributaryDb::is_fatally_slashed(self.txn, self.set, SeraiAddress(signer.to_bytes())) {
-        return;
-      }
-    }
-
-    match tx {
-      // Accumulate this vote and fatally slash the participant if past the threshold
-      Transaction::RemoveParticipant { participant, signed } => {
-        let signer = signer(signed);
-
-        // Check the participant voted to be removed actually exists
-        if !self.validators.iter().any(|validator| *validator == participant) {
-          TributaryDb::fatal_slash(
-            self.txn,
-            self.set,
-            signer,
-            "voted to remove non-existent participant",
-          );
-          return;
-        }
-
-        match TributaryDb::accumulate(
-          self.txn,
-          self.set,
-          self.validators,
-          self.total_weight,
-          block_number,
-          Topic::RemoveParticipant { participant },
-          signer,
-          self.validator_weights[&signer],
-          &(),
-        ) {
-          DataSet::None => {}
-          DataSet::Participating(_) => {
-            TributaryDb::fatal_slash(self.txn, self.set, participant, "voted to remove");
-          }
-        };
-      }
-
-      // Send the participation to the processor
-      Transaction::DkgParticipation { participation, signed } => {
-        TributaryDb::send_message(
-          self.txn,
-          self.set,
-          messages::key_gen::CoordinatorMessage::Participation {
-            session: self.set.session,
-            participant: todo!("TODO"),
-            participation,
-          },
-        );
-      }
-      Transaction::DkgConfirmationPreprocess { attempt, preprocess, signed } => {
-        // Accumulate the preprocesses into our own FROST attempt manager
-        todo!("TODO")
-      }
-      Transaction::DkgConfirmationShare { attempt, share, signed } => {
-        // Accumulate the shares into our own FROST attempt manager
-        todo!("TODO")
-      }
-
-      Transaction::Cosign { substrate_block_hash } => {
-        // Update the latest intended-to-be-cosigned Substrate block
-        TributaryDb::set_latest_substrate_block_to_cosign(self.txn, self.set, substrate_block_hash);
-        // Start a new cosign if we weren't already working on one
-        self.potentially_start_cosign();
-      }
-      Transaction::Cosigned { substrate_block_hash } => {
-        TributaryDb::finish_cosigning(self.txn, self.set);
-
-        // Fetch the latest intended-to-be-cosigned block
-        let Some(latest_substrate_block_to_cosign) =
-          TributaryDb::latest_substrate_block_to_cosign(self.txn, self.set)
-        else {
-          return;
-        };
-        // If this is the block we just cosigned, return, preventing us from signing it again
-        if latest_substrate_block_to_cosign == substrate_block_hash {
-          return;
-        }
-
-        // Since we do have a new cosign to work on, start it
-        self.potentially_start_cosign();
-      }
-      Transaction::SubstrateBlock { hash } => {
-        // Whitelist all of the IDs this Substrate block causes to be signed
-        todo!("TODO")
-      }
-      Transaction::Batch { hash } => {
-        // Whitelist the signing of this batch, publishing our own preprocess
-        todo!("TODO")
-      }
-
-      Transaction::SlashReport { slash_points, signed } => {
-        let signer = signer(signed);
-
-        if slash_points.len() != self.validators.len() {
-          TributaryDb::fatal_slash(
-            self.txn,
-            self.set,
-            signer,
-            "slash report was for a distinct amount of signers",
-          );
-          return;
-        }
-
-        // Accumulate, and if past the threshold, calculate *the* slash report and start signing it
-        match TributaryDb::accumulate(
-          self.txn,
-          self.set,
-          self.validators,
-          self.total_weight,
-          block_number,
-          Topic::SlashReport,
-          signer,
-          self.validator_weights[&signer],
-          &slash_points,
-        ) {
-          DataSet::None => {}
-          DataSet::Participating(data_set) => {
-            // Find the median reported slashes for this validator
-            // TODO: This lets 34% perform a fatal slash. Should that be allowed?
-            let mut median_slash_report = Vec::with_capacity(self.validators.len());
-            for i in 0 .. self.validators.len() {
-              let mut this_validator =
-                data_set.values().map(|report| report[i]).collect::<Vec<_>>();
-              this_validator.sort_unstable();
-              // Choose the median, where if there are two median values, the lower one is chosen
-              let median_index = if (this_validator.len() % 2) == 1 {
-                this_validator.len() / 2
-              } else {
-                (this_validator.len() / 2) - 1
-              };
-              median_slash_report.push(this_validator[median_index]);
-            }
-
-            // We only publish slashes for the `f` worst performers to:
-            // 1) Effect amnesty if there were network disruptions which affected everyone
-            // 2) Ensure the signing threshold doesn't have a disincentive to do their job
-
-            // Find the worst performer within the signing threshold's slash points
-            let f = (self.validators.len() - 1) / 3;
-            let worst_validator_in_supermajority_slash_points = {
-              let mut sorted_slash_points = median_slash_report.clone();
-              sorted_slash_points.sort_unstable();
-              // This won't be a valid index if `f == 0`, which means we don't have any validators
-              // to slash
-              let index_of_first_validator_to_slash = self.validators.len() - f;
-              let index_of_worst_validator_in_supermajority = index_of_first_validator_to_slash - 1;
-              sorted_slash_points[index_of_worst_validator_in_supermajority]
-            };
-
-            // Perform the amortization
-            for slash_points in &mut median_slash_report {
-              *slash_points =
-                slash_points.saturating_sub(worst_validator_in_supermajority_slash_points)
-            }
-            let amortized_slash_report = median_slash_report;
-
-            // Create the resulting slash report
-            let mut slash_report = vec![];
-            for (validator, points) in self.validators.iter().copied().zip(amortized_slash_report) {
-              if points != 0 {
-                slash_report.push(Slash { key: validator.into(), points });
-              }
-            }
-            assert!(slash_report.len() <= f);
-
-            // Recognize the topic for signing the slash report
-            TributaryDb::recognize_topic(
-              self.txn,
-              self.set,
-              Topic::Sign {
-                id: VariantSignId::SlashReport,
-                attempt: 0,
-                round: SigningProtocolRound::Preprocess,
-              },
-            );
-            // Send the message for the processor to start signing
-            TributaryDb::send_message(
-              self.txn,
-              self.set,
-              messages::coordinator::CoordinatorMessage::SignSlashReport {
-                session: self.set.session,
-                report: slash_report,
-              },
-            );
-          }
-        };
-      }
-
-      Transaction::Sign { id, attempt, round, data, signed } => {
-        let topic = Topic::Sign { id, attempt, round };
-        let signer = signer(signed);
-
-        if u64::try_from(data.len()).unwrap() != self.validator_weights[&signer] {
-          TributaryDb::fatal_slash(
-            self.txn,
-            self.set,
-            signer,
-            "signer signed with a distinct amount of key shares than they had key shares",
-          );
-          return;
-        }
-
-        match TributaryDb::accumulate(
-          self.txn,
-          self.set,
-          self.validators,
-          self.total_weight,
-          block_number,
-          topic,
-          signer,
-          self.validator_weights[&signer],
-          &data,
-        ) {
-          DataSet::None => {}
-          DataSet::Participating(data_set) => {
-            let id = topic.sign_id(self.set).expect("Topic::Sign didn't have SignId");
-            let flatten_data_set = |data_set| todo!("TODO");
-            let data_set = flatten_data_set(data_set);
-            TributaryDb::send_message(
-              self.txn,
-              self.set,
-              match round {
-                SigningProtocolRound::Preprocess => {
-                  messages::sign::CoordinatorMessage::Preprocesses { id, preprocesses: data_set }
-                }
-                SigningProtocolRound::Share => {
-                  messages::sign::CoordinatorMessage::Shares { id, shares: data_set }
-                }
-              },
-            )
-          }
-        };
-      }
-    }
-  }
-
-  fn handle_block(mut self, block_number: u64, block: Block<Transaction>) {
-    TributaryDb::start_of_block(self.txn, self.set, block_number);
-
-    for tx in block.transactions {
-      match tx {
-        TributaryTransaction::Tendermint(TendermintTx::SlashEvidence(ev)) => {
-          // Since the evidence is on the chain, it will have already been validated
-          // We can just punish the signer
-          let data = match ev {
-            Evidence::ConflictingMessages(first, second) => (first, Some(second)),
-            Evidence::InvalidPrecommit(first) | Evidence::InvalidValidRound(first) => (first, None),
-          };
-          /* TODO
-          let msgs = (
-            decode_signed_message::<TendermintNetwork<D, Transaction, P>>(&data.0).unwrap(),
-            if data.1.is_some() {
-              Some(
-                decode_signed_message::<TendermintNetwork<D, Transaction, P>>(&data.1.unwrap())
-                  .unwrap(),
-              )
-            } else {
-              None
-            },
-          );
-
-          // Since anything with evidence is fundamentally faulty behavior, not just temporal
-          // errors, mark the node as fatally slashed
-          TributaryDb::fatal_slash(
-            self.txn, msgs.0.msg.sender, &format!("invalid tendermint messages: {msgs:?}"));
-          */
-          todo!("TODO")
-        }
-        TributaryTransaction::Application(tx) => {
-          self.handle_application_tx(block_number, tx);
-        }
-      }
-    }
-  }
-}
-
-struct ScanTributaryTask<D: Db, TD: Db> {
-  db: D,
-  set: ValidatorSet,
-  validators: Vec<SeraiAddress>,
-  total_weight: u64,
-  validator_weights: HashMap<SeraiAddress, u64>,
-  tributary: TributaryReader<TD, Transaction>,
-}
-impl<D: Db, TD: Db> ContinuallyRan for ScanTributaryTask<D, TD> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
-    async move {
-      let (mut last_block_number, mut last_block_hash) =
-        TributaryDb::last_handled_tributary_block(&self.db, self.set)
-          .unwrap_or((0, self.tributary.genesis()));
-
-      let mut made_progess = false;
-      while let Some(next) = self.tributary.block_after(&last_block_hash) {
-        let block = self.tributary.block(&next).unwrap();
-        let block_number = last_block_number + 1;
-        let block_hash = block.hash();
-
-        // Make sure we have all of the provided transactions for this block
-        for tx in &block.transactions {
-          let TransactionKind::Provided(order) = tx.kind() else {
-            continue;
-          };
-
-          // make sure we have all the provided txs in this block locally
-          if !self.tributary.locally_provided_txs_in_block(&block_hash, order) {
-            return Err(format!(
-              "didn't have the provided Transactions on-chain for set (ephemeral error): {:?}",
-              self.set
-            ));
-          }
-        }
-
-        let mut txn = self.db.txn();
-        (ScanBlock {
-          txn: &mut txn,
-          set: self.set,
-          validators: &self.validators,
-          total_weight: self.total_weight,
-          validator_weights: &self.validator_weights,
-          tributary: &self.tributary,
-        })
-        .handle_block(block_number, block);
-        TributaryDb::set_last_handled_tributary_block(&mut txn, self.set, block_number, block_hash);
-        last_block_number = block_number;
-        last_block_hash = block_hash;
-        txn.commit();
-
-        made_progess = true;
-      }
-
-      Ok(made_progess)
-    }
-  }
-}

coordinator/src/tributary/transaction.rs

@@ -1,338 +0,0 @@
-use core::{ops::Deref, fmt::Debug};
-use std::io;
-
-use zeroize::Zeroizing;
-use rand_core::{RngCore, CryptoRng};
-
-use blake2::{digest::typenum::U32, Digest, Blake2b};
-use ciphersuite::{
-  group::{ff::Field, GroupEncoding},
-  Ciphersuite, Ristretto,
-};
-use schnorr::SchnorrSignature;
-
-use scale::Encode;
-use borsh::{BorshSerialize, BorshDeserialize};
-
-use serai_client::{primitives::SeraiAddress, validator_sets::primitives::MAX_KEY_SHARES_PER_SET};
-
-use messages::sign::VariantSignId;
-
-use tributary::{
-  ReadWrite,
-  transaction::{
-    Signed as TributarySigned, TransactionError, TransactionKind, Transaction as TransactionTrait,
-  },
-};
-
-/// The round this data is for, within a signing protocol.
-#[derive(Clone, Copy, PartialEq, Eq, Debug, Encode, BorshSerialize, BorshDeserialize)]
-pub enum SigningProtocolRound {
-  /// A preprocess.
-  Preprocess,
-  /// A signature share.
-  Share,
-}
-
-impl SigningProtocolRound {
-  fn nonce(&self) -> u32 {
-    match self {
-      SigningProtocolRound::Preprocess => 0,
-      SigningProtocolRound::Share => 1,
-    }
-  }
-}
-
-/// `tributary::Signed` but without the nonce.
-///
-/// All of our nonces are deterministic to the type of transaction and fields within.
-#[derive(Clone, Copy, PartialEq, Eq, Debug)]
-pub struct Signed {
-  /// The signer.
-  pub signer: <Ristretto as Ciphersuite>::G,
-  /// The signature.
-  pub signature: SchnorrSignature<Ristretto>,
-}
-
-impl BorshSerialize for Signed {
-  fn serialize<W: io::Write>(&self, writer: &mut W) -> Result<(), io::Error> {
-    writer.write_all(self.signer.to_bytes().as_ref())?;
-    self.signature.write(writer)
-  }
-}
-impl BorshDeserialize for Signed {
-  fn deserialize_reader<R: io::Read>(reader: &mut R) -> Result<Self, io::Error> {
-    let signer = Ristretto::read_G(reader)?;
-    let signature = SchnorrSignature::read(reader)?;
-    Ok(Self { signer, signature })
-  }
-}
-
-impl Signed {
-  /// Provide a nonce to convert a `Signed` into a `tributary::Signed`.
-  fn nonce(&self, nonce: u32) -> TributarySigned {
-    TributarySigned { signer: self.signer, nonce, signature: self.signature }
-  }
-}
-
-/// The Tributary transaction definition used by Serai
-#[derive(Clone, PartialEq, Eq, Debug, BorshSerialize, BorshDeserialize)]
-pub enum Transaction {
-  /// A vote to remove a participant for invalid behavior
-  RemoveParticipant {
-    /// The participant to remove
-    participant: SeraiAddress,
-    /// The transaction's signer and signature
-    signed: Signed,
-  },
-
-  /// A participation in the DKG
-  DkgParticipation {
-    participation: Vec<u8>,
-    /// The transaction's signer and signature
-    signed: Signed,
-  },
-  /// The preprocess to confirm the DKG results on-chain
-  DkgConfirmationPreprocess {
-    /// The attempt number of this signing protocol
-    attempt: u32,
-    // The preprocess
-    preprocess: [u8; 64],
-    /// The transaction's signer and signature
-    signed: Signed,
-  },
-  /// The signature share to confirm the DKG results on-chain
-  DkgConfirmationShare {
-    /// The attempt number of this signing protocol
-    attempt: u32,
-    // The signature share
-    share: [u8; 32],
-    /// The transaction's signer and signature
-    signed: Signed,
-  },
-
-  /// Intend to co-sign a finalized Substrate block
-  ///
-  /// When the time comes to start a new co-signing protocol, the most recent Substrate block will
-  /// be the one selected to be cosigned.
-  Cosign {
-    /// The hash of the Substrate block to sign
-    substrate_block_hash: [u8; 32],
-  },
-
-  /// The cosign for a Substrate block
-  ///
-  /// After producing this cosign, we need to start work on the latest intended-to-be cosigned
-  /// block. That requires agreement on when this cosign was produced, which we solve by embedding
-  /// this cosign on chain.
-  ///
-  /// We ideally don't have this transaction at all. The coordinator, without access to any of the
-  /// key shares, could observe the FROST signing session and determine a successful completion.
-  /// Unfortunately, that functionality is not present in modular-frost, so we do need to support
-  /// *some* asynchronous flow (where the processor or P2P network informs us of the successful
-  /// completion).
-  ///
-  /// If we use a `Provided` transaction, that requires everyone observe this cosign.
-  ///
-  /// If we use an `Unsigned` transaction, we can't verify the cosign signature inside
-  /// `Transaction::verify` unless we embedded the full `SignedCosign` on-chain. The issue is since
-  /// a Tributary is stateless with regards to the on-chain logic, including `Transaction::verify`,
-  /// we can't verify the signature against the group's public key unless we also include that (but
-  /// then we open a DoS where arbitrary group keys are specified to cause inclusion of arbitrary
-  /// blobs on chain).
-  ///
-  /// If we use a `Signed` transaction, we mitigate the DoS risk by having someone to fatally
-  /// slash. We have horrible performance though as for 100 validators, all 100 will publish this
-  /// transaction.
-  ///
-  /// We could use a signed `Unsigned` transaction, where it includes a signer and signature but
-  /// isn't technically a Signed transaction. This lets us de-duplicate the transaction premised on
-  /// its contents.
-  ///
-  /// The optimal choice is likely to use a `Provided` transaction. We don't actually need to
-  /// observe the produced cosign (which is ephemeral). As long as it's agreed the cosign in
-  /// question no longer needs to produced, which would mean the cosigning protocol at-large
-  /// cosigning the block in question, it'd be safe to provide this and move on to the next cosign.
-  Cosigned { substrate_block_hash: [u8; 32] },
-
-  /// Acknowledge a Substrate block
-  ///
-  /// This is provided after the block has been cosigned.
-  ///
-  /// With the acknowledgement of a Substrate block, we can whitelist all the `VariantSignId`s
-  /// resulting from its handling.
-  SubstrateBlock {
-    /// The hash of the Substrate block
-    hash: [u8; 32],
-  },
-
-  /// Acknowledge a Batch
-  ///
-  /// Once everyone has acknowledged the Batch, we can begin signing it.
-  Batch {
-    /// The hash of the Batch's serialization.
-    ///
-    /// Generally, we refer to a Batch by its ID/the hash of its instructions. Here, we want to
-    /// ensure consensus on the Batch, and achieving consensus on its hash is the most effective
-    /// way to do that.
-    hash: [u8; 32],
-  },
-
-  /// Data from a signing protocol.
-  Sign {
-    /// The ID of the object being signed
-    id: VariantSignId,
-    /// The attempt number of this signing protocol
-    attempt: u32,
-    /// The round this data is for, within the signing protocol
-    round: SigningProtocolRound,
-    /// The data itself
-    ///
-    /// There will be `n` blobs of data where `n` is the amount of key shares the validator sending
-    /// this transaction has.
-    data: Vec<Vec<u8>>,
-    /// The transaction's signer and signature
-    signed: Signed,
-  },
-
-  /// The local view of slashes observed by the transaction's sender
-  SlashReport {
-    /// The slash points accrued by each validator
-    slash_points: Vec<u32>,
-    /// The transaction's signer and signature
-    signed: Signed,
-  },
-}
-
-impl ReadWrite for Transaction {
-  fn read<R: io::Read>(reader: &mut R) -> io::Result<Self> {
-    borsh::from_reader(reader)
-  }
-
-  fn write<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
-    borsh::to_writer(writer, self)
-  }
-}
-
-impl TransactionTrait for Transaction {
-  fn kind(&self) -> TransactionKind {
-    match self {
-      Transaction::RemoveParticipant { participant, signed } => {
-        TransactionKind::Signed((b"RemoveParticipant", participant).encode(), signed.nonce(0))
-      }
-
-      Transaction::DkgParticipation { signed, .. } => {
-        TransactionKind::Signed(b"DkgParticipation".encode(), signed.nonce(0))
-      }
-      Transaction::DkgConfirmationPreprocess { attempt, signed, .. } => {
-        TransactionKind::Signed((b"DkgConfirmation", attempt).encode(), signed.nonce(0))
-      }
-      Transaction::DkgConfirmationShare { attempt, signed, .. } => {
-        TransactionKind::Signed((b"DkgConfirmation", attempt).encode(), signed.nonce(1))
-      }
-
-      Transaction::Cosign { .. } => TransactionKind::Provided("CosignSubstrateBlock"),
-      Transaction::Cosigned { .. } => TransactionKind::Provided("Cosigned"),
-      Transaction::SubstrateBlock { .. } => TransactionKind::Provided("SubstrateBlock"),
-      Transaction::Batch { .. } => TransactionKind::Provided("Batch"),
-
-      Transaction::Sign { id, attempt, round, signed, .. } => {
-        TransactionKind::Signed((b"Sign", id, attempt).encode(), signed.nonce(round.nonce()))
-      }
-
-      Transaction::SlashReport { signed, .. } => {
-        TransactionKind::Signed(b"SlashReport".encode(), signed.nonce(0))
-      }
-    }
-  }
-
-  fn hash(&self) -> [u8; 32] {
-    let mut tx = ReadWrite::serialize(self);
-    if let TransactionKind::Signed(_, signed) = self.kind() {
-      // Make sure the part we're cutting off is the signature
-      assert_eq!(tx.drain((tx.len() - 64) ..).collect::<Vec<_>>(), signed.signature.serialize());
-    }
-    Blake2b::<U32>::digest(&tx).into()
-  }
-
-  // This is a stateless verification which we use to enforce some size limits.
-  fn verify(&self) -> Result<(), TransactionError> {
-    #[allow(clippy::match_same_arms)]
-    match self {
-      // Fixed-length TX
-      Transaction::RemoveParticipant { .. } => {}
-
-      // TODO: MAX_DKG_PARTICIPATION_LEN
-      Transaction::DkgParticipation { .. } => {}
-      // These are fixed-length TXs
-      Transaction::DkgConfirmationPreprocess { .. } | Transaction::DkgConfirmationShare { .. } => {}
-
-      // Provided TXs
-      Transaction::Cosign { .. } |
-      Transaction::Cosigned { .. } |
-      Transaction::SubstrateBlock { .. } |
-      Transaction::Batch { .. } => {}
-
-      Transaction::Sign { data, .. } => {
-        if data.len() > usize::try_from(MAX_KEY_SHARES_PER_SET).unwrap() {
-          Err(TransactionError::InvalidContent)?
-        }
-        // TODO: MAX_SIGN_LEN
-      }
-
-      Transaction::SlashReport { slash_points, .. } => {
-        if slash_points.len() > usize::try_from(MAX_KEY_SHARES_PER_SET).unwrap() {
-          Err(TransactionError::InvalidContent)?
-        }
-      }
-    };
-    Ok(())
-  }
-}
-
-impl Transaction {
-  // Sign a transaction
-  //
-  // Panics if signing a transaction type which isn't `TransactionKind::Signed`
-  pub fn sign<R: RngCore + CryptoRng>(
-    &mut self,
-    rng: &mut R,
-    genesis: [u8; 32],
-    key: &Zeroizing<<Ristretto as Ciphersuite>::F>,
-  ) {
-    fn signed(tx: &mut Transaction) -> &mut Signed {
-      #[allow(clippy::match_same_arms)] // This doesn't make semantic sense here
-      match tx {
-        Transaction::RemoveParticipant { ref mut signed, .. } |
-        Transaction::DkgParticipation { ref mut signed, .. } |
-        Transaction::DkgConfirmationPreprocess { ref mut signed, .. } => signed,
-        Transaction::DkgConfirmationShare { ref mut signed, .. } => signed,
-
-        Transaction::Cosign { .. } => panic!("signing CosignSubstrateBlock"),
-        Transaction::Cosigned { .. } => panic!("signing Cosigned"),
-        Transaction::SubstrateBlock { .. } => panic!("signing SubstrateBlock"),
-        Transaction::Batch { .. } => panic!("signing Batch"),
-
-        Transaction::Sign { ref mut signed, .. } => signed,
-
-        Transaction::SlashReport { ref mut signed, .. } => signed,
-      }
-    }
-
-    // Decide the nonce to sign with
-    let sig_nonce = Zeroizing::new(<Ristretto as Ciphersuite>::F::random(rng));
-
-    {
-      // Set the signer and the nonce
-      let signed = signed(self);
-      signed.signer = Ristretto::generator() * key.deref();
-      signed.signature.R = <Ristretto as Ciphersuite>::generator() * sig_nonce.deref();
-    }
-
-    // Get the signature hash (which now includes `R || A` making it valid as the challenge)
-    let sig_hash = self.sig_hash(genesis);
-
-    // Sign the signature
-    signed(self).signature = SchnorrSignature::<Ristretto>::sign(key, sig_nonce, sig_hash);
-  }
-}

coordinator/substrate/Cargo.toml

@@ -18,7 +18,9 @@ rustdoc-args = ["--cfg", "docsrs"]
 workspace = true
 
 [dependencies]
-scale = { package = "parity-scale-codec", version = "3", default-features = false, features = ["std", "derive"] }
+bitvec = { version = "1", default-features = false, features = ["std"] }
+
+scale = { package = "parity-scale-codec", version = "3", default-features = false, features = ["std", "derive", "bit-vec"] }
 borsh = { version = "1", default-features = false, features = ["std", "derive", "de_strict_order"] }
 serai-client = { path = "../../substrate/client", version = "0.1", default-features = false, features = ["serai", "borsh"] }
 

coordinator/substrate/README.md

@@ -1,6 +1,6 @@
-# Serai Coordinate Substrate Scanner
+# Serai Coordinator Substrate
 
-This is the scanner of the Serai blockchain for the purposes of Serai's coordinator.
+This crate manages the Serai coordinators's interactions with Serai's Substrate blockchain.
 
 Two event streams are defined:
 
@@ -12,3 +12,9 @@ Two event streams are defined:
 The canonical event stream is available without provision of a validator's public key. The ephemeral
 event stream requires provision of a validator's public key. Both are ordered within themselves, yet
 there are no ordering guarantees across the two.
+
+Additionally, a collection of tasks are defined to publish data onto Serai:
+
+- `SetKeysTask`, which sets the keys generated via DKGs onto Serai.
+- `PublishBatchTask`, which publishes `Batch`s onto Serai.
+- `PublishSlashReportTask`, which publishes `SlashReport`s onto Serai.

coordinator/substrate/src/canonical.rs

@@ -1,4 +1,5 @@
-use std::future::Future;
+use core::future::Future;
+use std::sync::Arc;
 
 use futures::stream::{StreamExt, FuturesOrdered};
 
@@ -20,20 +21,22 @@ create_db!(
 /// The event stream for canonical events.
 pub struct CanonicalEventStream<D: Db> {
   db: D,
-  serai: Serai,
+  serai: Arc<Serai>,
 }
 
 impl<D: Db> CanonicalEventStream<D> {
   /// Create a new canonical event stream.
   ///
   /// Only one of these may exist over the provided database.
-  pub fn new(db: D, serai: Serai) -> Self {
+  pub fn new(db: D, serai: Arc<Serai>) -> Self {
     Self { db, serai }
   }
 }
 
 impl<D: Db> ContinuallyRan for CanonicalEventStream<D> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = String;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       let next_block = NextBlock::get(&self.db).unwrap_or(0);
       let latest_finalized_block =

coordinator/substrate/src/ephemeral.rs

@@ -1,4 +1,5 @@
-use std::future::Future;
+use core::future::Future;
+use std::sync::Arc;
 
 use futures::stream::{StreamExt, FuturesOrdered};
 
@@ -24,7 +25,7 @@ create_db!(
 /// The event stream for ephemeral events.
 pub struct EphemeralEventStream<D: Db> {
   db: D,
-  serai: Serai,
+  serai: Arc<Serai>,
   validator: PublicKey,
 }
 
@@ -32,13 +33,15 @@ impl<D: Db> EphemeralEventStream<D> {
   /// Create a new ephemeral event stream.
   ///
   /// Only one of these may exist over the provided database.
-  pub fn new(db: D, serai: Serai, validator: PublicKey) -> Self {
+  pub fn new(db: D, serai: Arc<Serai>, validator: PublicKey) -> Self {
     Self { db, serai, validator }
   }
 }
 
 impl<D: Db> ContinuallyRan for EphemeralEventStream<D> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = String;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       let next_block = NextBlock::get(&self.db).unwrap_or(0);
       let latest_finalized_block =
@@ -156,8 +159,9 @@ impl<D: Db> ContinuallyRan for EphemeralEventStream<D> {
               Err("validator's weight exceeded u16::MAX".to_string())?
             };
 
+            // Do the summation in u32 so we don't risk a u16 overflow
             let total_weight = validators.iter().map(|(_, weight)| u32::from(*weight)).sum::<u32>();
-            if total_weight > MAX_KEY_SHARES_PER_SET {
+            if total_weight > u32::from(MAX_KEY_SHARES_PER_SET) {
               Err(format!(
                 "{set:?} has {total_weight} key shares when the max is {MAX_KEY_SHARES_PER_SET}"
               ))?;
@@ -216,7 +220,7 @@ impl<D: Db> ContinuallyRan for EphemeralEventStream<D> {
               &NewSetInformation {
                 set: *set,
                 serai_block: block.block_hash,
-                start_time: block.time,
+                declaration_time: block.time,
                 // TODO: Why do we have this as an explicit field here?
                 // Shouldn't thiis be inlined into the Processor's key gen code, where it's used?
                 threshold: ((total_weight * 2) / 3) + 1,
@@ -233,7 +237,7 @@ impl<D: Db> ContinuallyRan for EphemeralEventStream<D> {
           else {
             panic!("AcceptedHandover event wasn't a AcceptedHandover event: {accepted_handover:?}");
           };
-          crate::SignSlashReport::send(&mut txn, set);
+          crate::SignSlashReport::send(&mut txn, *set);
         }
 
         txn.commit();

coordinator/substrate/src/lib.rs

@@ -6,14 +6,25 @@ use scale::{Encode, Decode};
 use borsh::{io, BorshSerialize, BorshDeserialize};
 
 use serai_client::{
-  primitives::{PublicKey, NetworkId},
-  validator_sets::primitives::ValidatorSet,
+  primitives::{NetworkId, PublicKey, Signature, SeraiAddress},
+  validator_sets::primitives::{Session, ValidatorSet, KeyPair},
+  in_instructions::primitives::SignedBatch,
+  Transaction,
 };
 
 use serai_db::*;
 
 mod canonical;
+pub use canonical::CanonicalEventStream;
 mod ephemeral;
+pub use ephemeral::EphemeralEventStream;
+
+mod set_keys;
+pub use set_keys::SetKeysTask;
+mod publish_batch;
+pub use publish_batch::PublishBatchTask;
+mod publish_slash_report;
+pub use publish_slash_report::PublishSlashReportTask;
 
 fn borsh_serialize_validators<W: io::Write>(
   validators: &Vec<(PublicKey, u16)>,
@@ -30,26 +41,28 @@ fn borsh_deserialize_validators<R: io::Read>(
 }
 
 /// The information for a new set.
-#[derive(Debug, BorshSerialize, BorshDeserialize)]
+#[derive(Clone, Debug, BorshSerialize, BorshDeserialize)]
 pub struct NewSetInformation {
-  set: ValidatorSet,
-  serai_block: [u8; 32],
-  start_time: u64,
-  threshold: u16,
+  /// The set.
+  pub set: ValidatorSet,
+  /// The Serai block which declared it.
+  pub serai_block: [u8; 32],
+  /// The time of the block which declared it, in seconds.
+  pub declaration_time: u64,
+  /// The threshold to use.
+  pub threshold: u16,
+  /// The validators, with the amount of key shares they have.
   #[borsh(
     serialize_with = "borsh_serialize_validators",
     deserialize_with = "borsh_deserialize_validators"
   )]
-  validators: Vec<(PublicKey, u16)>,
-  evrf_public_keys: Vec<([u8; 32], Vec<u8>)>,
+  pub validators: Vec<(PublicKey, u16)>,
+  /// The eVRF public keys.
+  pub evrf_public_keys: Vec<([u8; 32], Vec<u8>)>,
 }
 
 mod _public_db {
-  use serai_client::{primitives::NetworkId, validator_sets::primitives::ValidatorSet};
-
-  use serai_db::*;
-
-  use crate::NewSetInformation;
+  use super::*;
 
   db_channel!(
     CoordinatorSubstrate {
@@ -58,8 +71,20 @@ mod _public_db {
 
       // Relevant new set, from an ephemeral event stream
       NewSet: () -> NewSetInformation,
-      // Relevant sign slash report, from an ephemeral event stream
-      SignSlashReport: () -> ValidatorSet,
+      // Potentially relevant sign slash report, from an ephemeral event stream
+      SignSlashReport: (set: ValidatorSet) -> (),
+
+      // Signed batches to publish onto the Serai network
+      SignedBatches: (network: NetworkId) -> SignedBatch,
+    }
+  );
+
+  create_db!(
+    CoordinatorSubstrate {
+      // Keys to set on the Serai network
+      Keys: (network: NetworkId) -> (Session, Vec<u8>),
+      // Slash reports to publish onto the Serai network
+      SlashReports: (network: NetworkId) -> (Session, Vec<u8>),
     }
   );
 }
@@ -101,12 +126,103 @@ impl NewSet {
 /// notifications for all relevant validator sets will be included.
 pub struct SignSlashReport;
 impl SignSlashReport {
-  pub(crate) fn send(txn: &mut impl DbTxn, set: &ValidatorSet) {
-    _public_db::SignSlashReport::send(txn, set);
+  pub(crate) fn send(txn: &mut impl DbTxn, set: ValidatorSet) {
+    _public_db::SignSlashReport::send(txn, set, &());
   }
   /// Try to receive a notification to sign a slash report, returning `None` if there is none to
   /// receive.
-  pub fn try_recv(txn: &mut impl DbTxn) -> Option<ValidatorSet> {
-    _public_db::SignSlashReport::try_recv(txn)
+  pub fn try_recv(txn: &mut impl DbTxn, set: ValidatorSet) -> Option<()> {
+    _public_db::SignSlashReport::try_recv(txn, set)
+  }
+}
+
+/// The keys to set on Serai.
+pub struct Keys;
+impl Keys {
+  /// Set the keys to report for a validator set.
+  ///
+  /// This only saves the most recent keys as only a single session is eligible to have its keys
+  /// reported at once.
+  pub fn set(
+    txn: &mut impl DbTxn,
+    set: ValidatorSet,
+    key_pair: KeyPair,
+    signature_participants: bitvec::vec::BitVec<u8, bitvec::order::Lsb0>,
+    signature: Signature,
+  ) {
+    // If we have a more recent pair of keys, don't write this historic one
+    if let Some((existing_session, _)) = _public_db::Keys::get(txn, set.network) {
+      if existing_session.0 >= set.session.0 {
+        return;
+      }
+    }
+
+    let tx = serai_client::validator_sets::SeraiValidatorSets::set_keys(
+      set.network,
+      key_pair,
+      signature_participants,
+      signature,
+    );
+    _public_db::Keys::set(txn, set.network, &(set.session, tx.encode()));
+  }
+  pub(crate) fn take(txn: &mut impl DbTxn, network: NetworkId) -> Option<(Session, Transaction)> {
+    let (session, tx) = _public_db::Keys::take(txn, network)?;
+    Some((session, <_>::decode(&mut tx.as_slice()).unwrap()))
+  }
+}
+
+/// The signed batches to publish onto Serai.
+pub struct SignedBatches;
+impl SignedBatches {
+  /// Send a `SignedBatch` to publish onto Serai.
+  ///
+  /// These will be published sequentially. Out-of-order sending risks hanging the task.
+  pub fn send(txn: &mut impl DbTxn, batch: &SignedBatch) {
+    _public_db::SignedBatches::send(txn, batch.batch.network, batch);
+  }
+  pub(crate) fn try_recv(txn: &mut impl DbTxn, network: NetworkId) -> Option<SignedBatch> {
+    _public_db::SignedBatches::try_recv(txn, network)
+  }
+}
+
+/// The slash report was invalid.
+#[derive(Debug)]
+pub struct InvalidSlashReport;
+
+/// The slash reports to publish onto Serai.
+pub struct SlashReports;
+impl SlashReports {
+  /// Set the slashes to report for a validator set.
+  ///
+  /// This only saves the most recent slashes as only a single session is eligible to have its
+  /// slashes reported at once.
+  ///
+  /// Returns Err if the slashes are invalid. Returns Ok if the slashes weren't detected as
+  /// invalid. Slashes may be considered invalid by the Serai blockchain later even if not detected
+  /// as invalid here.
+  pub fn set(
+    txn: &mut impl DbTxn,
+    set: ValidatorSet,
+    slashes: Vec<(SeraiAddress, u32)>,
+    signature: Signature,
+  ) -> Result<(), InvalidSlashReport> {
+    // If we have a more recent slash report, don't write this historic one
+    if let Some((existing_session, _)) = _public_db::SlashReports::get(txn, set.network) {
+      if existing_session.0 >= set.session.0 {
+        return Ok(());
+      }
+    }
+
+    let tx = serai_client::validator_sets::SeraiValidatorSets::report_slashes(
+      set.network,
+      slashes.try_into().map_err(|_| InvalidSlashReport)?,
+      signature,
+    );
+    _public_db::SlashReports::set(txn, set.network, &(set.session, tx.encode()));
+    Ok(())
+  }
+  pub(crate) fn take(txn: &mut impl DbTxn, network: NetworkId) -> Option<(Session, Transaction)> {
+    let (session, tx) = _public_db::SlashReports::take(txn, network)?;
+    Some((session, <_>::decode(&mut tx.as_slice()).unwrap()))
   }
 }

coordinator/substrate/src/publish_batch.rs

@@ -0,0 +1,66 @@
+use core::future::Future;
+use std::sync::Arc;
+
+use serai_db::{DbTxn, Db};
+
+use serai_client::{primitives::NetworkId, SeraiError, Serai};
+
+use serai_task::ContinuallyRan;
+
+use crate::SignedBatches;
+
+/// Publish `SignedBatch`s from `SignedBatches` onto Serai.
+pub struct PublishBatchTask<D: Db> {
+  db: D,
+  serai: Arc<Serai>,
+  network: NetworkId,
+}
+
+impl<D: Db> PublishBatchTask<D> {
+  /// Create a task to publish `SignedBatch`s onto Serai.
+  ///
+  /// Returns None if `network == NetworkId::Serai`.
+  // TODO: ExternalNetworkId
+  pub fn new(db: D, serai: Arc<Serai>, network: NetworkId) -> Option<Self> {
+    if network == NetworkId::Serai {
+      None?
+    };
+    Some(Self { db, serai, network })
+  }
+}
+
+impl<D: Db> ContinuallyRan for PublishBatchTask<D> {
+  type Error = SeraiError;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
+    async move {
+      let mut made_progress = false;
+
+      loop {
+        let mut txn = self.db.txn();
+        let Some(batch) = SignedBatches::try_recv(&mut txn, self.network) else {
+          // No batch to publish at this time
+          break;
+        };
+
+        // Publish this Batch if it hasn't already been published
+        let serai = self.serai.as_of_latest_finalized_block().await?;
+        let last_batch = serai.in_instructions().last_batch_for_network(self.network).await?;
+        if last_batch < Some(batch.batch.id) {
+          // This stream of Batches *should* be sequential within the larger context of the Serai
+          // coordinator. In this library, we use a more relaxed definition and don't assert
+          // sequence. This does risk hanging the task, if Batch #n+1 is sent before Batch #n, but
+          // that is a documented fault of the `SignedBatches` API.
+          self
+            .serai
+            .publish(&serai_client::in_instructions::SeraiInInstructions::execute_batch(batch))
+            .await?;
+        }
+
+        txn.commit();
+        made_progress = true;
+      }
+      Ok(made_progress)
+    }
+  }
+}

coordinator/substrate/src/publish_slash_report.rs

@@ -0,0 +1,89 @@
+use core::future::Future;
+use std::sync::Arc;
+
+use serai_db::{DbTxn, Db};
+
+use serai_client::{primitives::NetworkId, validator_sets::primitives::Session, Serai};
+
+use serai_task::ContinuallyRan;
+
+use crate::SlashReports;
+
+/// Publish slash reports from `SlashReports` onto Serai.
+pub struct PublishSlashReportTask<D: Db> {
+  db: D,
+  serai: Arc<Serai>,
+}
+
+impl<D: Db> PublishSlashReportTask<D> {
+  /// Create a task to publish slash reports onto Serai.
+  pub fn new(db: D, serai: Arc<Serai>) -> Self {
+    Self { db, serai }
+  }
+}
+
+impl<D: Db> ContinuallyRan for PublishSlashReportTask<D> {
+  type Error = String;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
+    async move {
+      let mut made_progress = false;
+      for network in serai_client::primitives::NETWORKS {
+        if network == NetworkId::Serai {
+          continue;
+        };
+
+        let mut txn = self.db.txn();
+        let Some((session, slash_report)) = SlashReports::take(&mut txn, network) else {
+          // No slash report to publish
+          continue;
+        };
+
+        let serai =
+          self.serai.as_of_latest_finalized_block().await.map_err(|e| format!("{e:?}"))?;
+        let serai = serai.validator_sets();
+        let session_after_slash_report = Session(session.0 + 1);
+        let current_session = serai.session(network).await.map_err(|e| format!("{e:?}"))?;
+        let current_session = current_session.map(|session| session.0);
+        // Only attempt to publish the slash report for session #n while session #n+1 is still
+        // active
+        let session_after_slash_report_retired =
+          current_session > Some(session_after_slash_report.0);
+        if session_after_slash_report_retired {
+          // Commit the txn to drain this slash report from the database and not try it again later
+          txn.commit();
+          continue;
+        }
+
+        if Some(session_after_slash_report.0) != current_session {
+          // We already checked the current session wasn't greater, and they're not equal
+          assert!(current_session < Some(session_after_slash_report.0));
+          // This would mean the Serai node is resyncing and is behind where it prior was
+          Err("have a slash report for a session Serai has yet to retire".to_string())?;
+        }
+
+        // If this session which should publish a slash report already has, move on
+        let key_pending_slash_report =
+          serai.key_pending_slash_report(network).await.map_err(|e| format!("{e:?}"))?;
+        if key_pending_slash_report.is_none() {
+          txn.commit();
+          continue;
+        };
+
+        match self.serai.publish(&slash_report).await {
+          Ok(()) => {
+            txn.commit();
+            made_progress = true;
+          }
+          // This could be specific to this TX (such as an already in mempool error) and it may be
+          // worthwhile to continue iteration with the other pending slash reports. We assume this
+          // error ephemeral and that the latency incurred for this ephemeral error to resolve is
+          // miniscule compared to the window available to publish the slash report. That makes
+          // this a non-issue.
+          Err(e) => Err(format!("couldn't publish slash report transaction: {e:?}"))?,
+        }
+      }
+      Ok(made_progress)
+    }
+  }
+}

coordinator/substrate/src/set_keys.rs

@@ -0,0 +1,88 @@
+use core::future::Future;
+use std::sync::Arc;
+
+use serai_db::{DbTxn, Db};
+
+use serai_client::{primitives::NetworkId, validator_sets::primitives::ValidatorSet, Serai};
+
+use serai_task::ContinuallyRan;
+
+use crate::Keys;
+
+/// Set keys from `Keys` on Serai.
+pub struct SetKeysTask<D: Db> {
+  db: D,
+  serai: Arc<Serai>,
+}
+
+impl<D: Db> SetKeysTask<D> {
+  /// Create a task to publish slash reports onto Serai.
+  pub fn new(db: D, serai: Arc<Serai>) -> Self {
+    Self { db, serai }
+  }
+}
+
+impl<D: Db> ContinuallyRan for SetKeysTask<D> {
+  type Error = String;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
+    async move {
+      let mut made_progress = false;
+      for network in serai_client::primitives::NETWORKS {
+        if network == NetworkId::Serai {
+          continue;
+        };
+
+        let mut txn = self.db.txn();
+        let Some((session, keys)) = Keys::take(&mut txn, network) else {
+          // No keys to set
+          continue;
+        };
+
+        let serai =
+          self.serai.as_of_latest_finalized_block().await.map_err(|e| format!("{e:?}"))?;
+        let serai = serai.validator_sets();
+        let current_session = serai.session(network).await.map_err(|e| format!("{e:?}"))?;
+        let current_session = current_session.map(|session| session.0);
+        // Only attempt to set these keys if this isn't a retired session
+        if Some(session.0) < current_session {
+          // Commit the txn to take these keys from the database and not try it again later
+          txn.commit();
+          continue;
+        }
+
+        if Some(session.0) != current_session {
+          // We already checked the current session wasn't greater, and they're not equal
+          assert!(current_session < Some(session.0));
+          // This would mean the Serai node is resyncing and is behind where it prior was
+          Err("have a keys for a session Serai has yet to start".to_string())?;
+        }
+
+        // If this session already has had its keys set, move on
+        if serai
+          .keys(ValidatorSet { network, session })
+          .await
+          .map_err(|e| format!("{e:?}"))?
+          .is_some()
+        {
+          txn.commit();
+          continue;
+        };
+
+        match self.serai.publish(&keys).await {
+          Ok(()) => {
+            txn.commit();
+            made_progress = true;
+          }
+          // This could be specific to this TX (such as an already in mempool error) and it may be
+          // worthwhile to continue iteration with the other pending slash reports. We assume this
+          // error ephemeral and that the latency incurred for this ephemeral error to resolve is
+          // miniscule compared to the window reasonable to set the keys. That makes this a
+          // non-issue.
+          Err(e) => Err(format!("couldn't publish set keys transaction: {e:?}"))?,
+        }
+      }
+      Ok(made_progress)
+    }
+  }
+}

coordinator/tributary-sdk/Cargo.toml

@@ -0,0 +1,49 @@
+[package]
+name = "tributary-sdk"
+version = "0.1.0"
+description = "A micro-blockchain to provide consensus and ordering to P2P communication"
+license = "AGPL-3.0-only"
+repository = "https://github.com/serai-dex/serai/tree/develop/coordinator/tributary-sdk"
+authors = ["Luke Parker <lukeparker5132@gmail.com>"]
+edition = "2021"
+rust-version = "1.81"
+
+[package.metadata.docs.rs]
+all-features = true
+rustdoc-args = ["--cfg", "docsrs"]
+
+[lints]
+workspace = true
+
+[dependencies]
+thiserror = { version = "2", default-features = false, features = ["std"] }
+
+subtle = { version = "^2", default-features = false, features = ["std"] }
+zeroize = { version = "^1.5", default-features = false, features = ["std"] }
+
+rand = { version = "0.8", default-features = false, features = ["std"] }
+rand_chacha = { version = "0.3", default-features = false, features = ["std"] }
+
+blake2 = { version = "0.10", default-features = false, features = ["std"] }
+transcript = { package = "flexible-transcript", path = "../../crypto/transcript", version = "0.3", default-features = false, features = ["std", "recommended"] }
+
+ciphersuite = { package = "ciphersuite", path = "../../crypto/ciphersuite", version = "0.4", default-features = false, features = ["std", "ristretto"] }
+schnorr = { package = "schnorr-signatures", path = "../../crypto/schnorr", version = "0.5", default-features = false, features = ["std"] }
+
+hex = { version = "0.4", default-features = false, features = ["std"] }
+log = { version = "0.4", default-features = false, features = ["std"] }
+
+serai-db = { path = "../../common/db", version = "0.1" }
+
+scale = { package = "parity-scale-codec", version = "3", default-features = false, features = ["std", "derive"] }
+futures-util = { version = "0.3", default-features = false, features = ["std", "sink", "channel"] }
+futures-channel = { version = "0.3", default-features = false, features = ["std", "sink"] }
+tendermint = { package = "tendermint-machine", path = "./tendermint", version = "0.2" }
+
+tokio = { version = "1", default-features = false, features = ["sync", "time", "rt"] }
+
+[dev-dependencies]
+tokio = { version = "1", features = ["macros"] }
+
+[features]
+tests = []

coordinator/tributary-sdk/LICENSE

@@ -0,0 +1,15 @@
+AGPL-3.0-only license
+
+Copyright (c) 2023 Luke Parker
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU Affero General Public License Version 3 as
+published by the Free Software Foundation.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program. If not, see <http://www.gnu.org/licenses/>.

coordinator/tributary-sdk/README.md

@@ -0,0 +1,3 @@
+# Tributary
+
+A verifiable, ordered broadcast layer implemented as a BFT micro-blockchain.

coordinator/tributary-sdk/src/lib.rs

@@ -0,0 +1,388 @@
+use core::{marker::PhantomData, fmt::Debug, future::Future};
+use std::{sync::Arc, io};
+
+use zeroize::Zeroizing;
+
+use ciphersuite::{Ciphersuite, Ristretto};
+
+use scale::Decode;
+use futures_channel::mpsc::UnboundedReceiver;
+use futures_util::{StreamExt, SinkExt};
+use ::tendermint::{
+  ext::{BlockNumber, Commit, Block as BlockTrait, Network},
+  SignedMessageFor, SyncedBlock, SyncedBlockSender, SyncedBlockResultReceiver, MessageSender,
+  TendermintMachine, TendermintHandle,
+};
+
+pub use ::tendermint::Evidence;
+
+use serai_db::Db;
+
+use tokio::sync::RwLock;
+
+mod merkle;
+pub(crate) use merkle::*;
+
+pub mod transaction;
+pub use transaction::{TransactionError, Signed, TransactionKind, Transaction as TransactionTrait};
+
+use crate::tendermint::tx::TendermintTx;
+
+mod provided;
+pub(crate) use provided::*;
+pub use provided::ProvidedError;
+
+mod block;
+pub use block::*;
+
+mod blockchain;
+pub(crate) use blockchain::*;
+
+mod mempool;
+pub(crate) use mempool::*;
+
+pub mod tendermint;
+pub(crate) use crate::tendermint::*;
+
+#[cfg(any(test, feature = "tests"))]
+pub mod tests;
+
+/// Size limit for an individual transaction.
+// This needs to be big enough to participate in a 101-of-150 eVRF DKG with each element taking
+// `MAX_KEY_LEN`. This also needs to be big enough to pariticpate in signing 520 Bitcoin inputs
+// with 49 key shares, and signing 120 Monero inputs with 49 key shares.
+// TODO: Add a test for these properties
+pub const TRANSACTION_SIZE_LIMIT: usize = 2_000_000;
+/// Amount of transactions a single account may have in the mempool.
+pub const ACCOUNT_MEMPOOL_LIMIT: u32 = 50;
+/// Block size limit.
+// This targets a growth limit of roughly 30 GB a day, under load, in order to prevent a malicious
+// participant from flooding disks and causing out of space errors in order processes.
+pub const BLOCK_SIZE_LIMIT: usize = 2_001_000;
+
+pub(crate) const TENDERMINT_MESSAGE: u8 = 0;
+pub(crate) const TRANSACTION_MESSAGE: u8 = 1;
+
+#[allow(clippy::large_enum_variant)]
+#[derive(Clone, PartialEq, Eq, Debug)]
+pub enum Transaction<T: TransactionTrait> {
+  Tendermint(TendermintTx),
+  Application(T),
+}
+
+impl<T: TransactionTrait> ReadWrite for Transaction<T> {
+  fn read<R: io::Read>(reader: &mut R) -> io::Result<Self> {
+    let mut kind = [0];
+    reader.read_exact(&mut kind)?;
+    match kind[0] {
+      0 => {
+        let tx = TendermintTx::read(reader)?;
+        Ok(Transaction::Tendermint(tx))
+      }
+      1 => {
+        let tx = T::read(reader)?;
+        Ok(Transaction::Application(tx))
+      }
+      _ => Err(io::Error::other("invalid transaction type")),
+    }
+  }
+  fn write<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
+    match self {
+      Transaction::Tendermint(tx) => {
+        writer.write_all(&[0])?;
+        tx.write(writer)
+      }
+      Transaction::Application(tx) => {
+        writer.write_all(&[1])?;
+        tx.write(writer)
+      }
+    }
+  }
+}
+
+impl<T: TransactionTrait> Transaction<T> {
+  pub fn hash(&self) -> [u8; 32] {
+    match self {
+      Transaction::Tendermint(tx) => tx.hash(),
+      Transaction::Application(tx) => tx.hash(),
+    }
+  }
+
+  pub fn kind(&self) -> TransactionKind {
+    match self {
+      Transaction::Tendermint(tx) => tx.kind(),
+      Transaction::Application(tx) => tx.kind(),
+    }
+  }
+}
+
+/// An item which can be read and written.
+pub trait ReadWrite: Sized {
+  fn read<R: io::Read>(reader: &mut R) -> io::Result<Self>;
+  fn write<W: io::Write>(&self, writer: &mut W) -> io::Result<()>;
+
+  fn serialize(&self) -> Vec<u8> {
+    // BlockHeader is 64 bytes and likely the smallest item in this system
+    let mut buf = Vec::with_capacity(64);
+    self.write(&mut buf).unwrap();
+    buf
+  }
+}
+
+pub trait P2p: 'static + Send + Sync + Clone {
+  /// Broadcast a message to all other members of the Tributary with the specified genesis.
+  ///
+  /// The Tributary will re-broadcast consensus messages on a fixed interval to ensure they aren't
+  /// prematurely dropped from the P2P layer. THe P2P layer SHOULD perform content-based
+  /// deduplication to ensure a sane amount of load.
+  fn broadcast(&self, genesis: [u8; 32], msg: Vec<u8>) -> impl Send + Future<Output = ()>;
+}
+
+impl<P: P2p> P2p for Arc<P> {
+  fn broadcast(&self, genesis: [u8; 32], msg: Vec<u8>) -> impl Send + Future<Output = ()> {
+    P::broadcast(self, genesis, msg)
+  }
+}
+
+#[derive(Clone)]
+pub struct Tributary<D: Db, T: TransactionTrait, P: P2p> {
+  db: D,
+
+  genesis: [u8; 32],
+  network: TendermintNetwork<D, T, P>,
+
+  synced_block: Arc<RwLock<SyncedBlockSender<TendermintNetwork<D, T, P>>>>,
+  synced_block_result: Arc<RwLock<SyncedBlockResultReceiver>>,
+  messages: Arc<RwLock<MessageSender<TendermintNetwork<D, T, P>>>>,
+}
+
+impl<D: Db, T: TransactionTrait, P: P2p> Tributary<D, T, P> {
+  pub async fn new(
+    db: D,
+    genesis: [u8; 32],
+    start_time: u64,
+    key: Zeroizing<<Ristretto as Ciphersuite>::F>,
+    validators: Vec<(<Ristretto as Ciphersuite>::G, u64)>,
+    p2p: P,
+  ) -> Option<Self> {
+    log::info!("new Tributary with genesis {}", hex::encode(genesis));
+
+    let validators_vec = validators.iter().map(|validator| validator.0).collect::<Vec<_>>();
+
+    let signer = Arc::new(Signer::new(genesis, key));
+    let validators = Arc::new(Validators::new(genesis, validators)?);
+
+    let mut blockchain = Blockchain::new(db.clone(), genesis, &validators_vec);
+    let block_number = BlockNumber(blockchain.block_number());
+
+    let start_time = if let Some(commit) = blockchain.commit(&blockchain.tip()) {
+      Commit::<Validators>::decode(&mut commit.as_ref()).unwrap().end_time
+    } else {
+      start_time
+    };
+    let proposal = TendermintBlock(
+      blockchain.build_block::<TendermintNetwork<D, T, P>>(&validators).serialize(),
+    );
+    let blockchain = Arc::new(RwLock::new(blockchain));
+
+    let network = TendermintNetwork { genesis, signer, validators, blockchain, p2p };
+
+    let TendermintHandle { synced_block, synced_block_result, messages, machine } =
+      TendermintMachine::new(
+        db.clone(),
+        network.clone(),
+        genesis,
+        block_number,
+        start_time,
+        proposal,
+      )
+      .await;
+    tokio::spawn(machine.run());
+
+    Some(Self {
+      db,
+      genesis,
+      network,
+      synced_block: Arc::new(RwLock::new(synced_block)),
+      synced_block_result: Arc::new(RwLock::new(synced_block_result)),
+      messages: Arc::new(RwLock::new(messages)),
+    })
+  }
+
+  pub fn block_time() -> u32 {
+    TendermintNetwork::<D, T, P>::block_time()
+  }
+
+  pub fn genesis(&self) -> [u8; 32] {
+    self.genesis
+  }
+
+  pub async fn block_number(&self) -> u64 {
+    self.network.blockchain.read().await.block_number()
+  }
+  pub async fn tip(&self) -> [u8; 32] {
+    self.network.blockchain.read().await.tip()
+  }
+
+  pub fn reader(&self) -> TributaryReader<D, T> {
+    TributaryReader(self.db.clone(), self.genesis, PhantomData)
+  }
+
+  pub async fn provide_transaction(&self, tx: T) -> Result<(), ProvidedError> {
+    self.network.blockchain.write().await.provide_transaction(tx)
+  }
+
+  pub async fn next_nonce(
+    &self,
+    signer: &<Ristretto as Ciphersuite>::G,
+    order: &[u8],
+  ) -> Option<u32> {
+    self.network.blockchain.read().await.next_nonce(signer, order)
+  }
+
+  // Returns Ok(true) if new, Ok(false) if an already present unsigned, or the error.
+  // Safe to be &self since the only meaningful usage of self is self.network.blockchain which
+  // successfully acquires its own write lock
+  pub async fn add_transaction(&self, tx: T) -> Result<bool, TransactionError> {
+    let tx = Transaction::Application(tx);
+    let mut to_broadcast = vec![TRANSACTION_MESSAGE];
+    tx.write(&mut to_broadcast).unwrap();
+    let res = self.network.blockchain.write().await.add_transaction::<TendermintNetwork<D, T, P>>(
+      true,
+      tx,
+      &self.network.signature_scheme(),
+    );
+    if res == Ok(true) {
+      self.network.p2p.broadcast(self.genesis, to_broadcast).await;
+    }
+    res
+  }
+
+  async fn sync_block_internal(
+    &self,
+    block: Block<T>,
+    commit: Vec<u8>,
+    result: &mut UnboundedReceiver<bool>,
+  ) -> bool {
+    let (tip, block_number) = {
+      let blockchain = self.network.blockchain.read().await;
+      (blockchain.tip(), blockchain.block_number())
+    };
+
+    if block.header.parent != tip {
+      log::debug!("told to sync a block whose parent wasn't our tip");
+      return false;
+    }
+
+    let block = TendermintBlock(block.serialize());
+    let mut commit_ref = commit.as_ref();
+    let Ok(commit) = Commit::<Arc<Validators>>::decode(&mut commit_ref) else {
+      log::error!("sent an invalidly serialized commit");
+      return false;
+    };
+    // Storage DoS vector. We *could* truncate to solely the relevant portion, trying to save this,
+    // yet then we'd have to test the truncation was performed correctly.
+    if !commit_ref.is_empty() {
+      log::error!("sent an commit with additional data after it");
+      return false;
+    }
+    if !self.network.verify_commit(block.id(), &commit) {
+      log::error!("sent an invalid commit");
+      return false;
+    }
+
+    let number = BlockNumber(block_number + 1);
+    self.synced_block.write().await.send(SyncedBlock { number, block, commit }).await.unwrap();
+    result.next().await.unwrap()
+  }
+
+  // Sync a block.
+  // TODO: Since we have a static validator set, we should only need the tail commit?
+  pub async fn sync_block(&self, block: Block<T>, commit: Vec<u8>) -> bool {
+    let mut result = self.synced_block_result.write().await;
+    self.sync_block_internal(block, commit, &mut result).await
+  }
+
+  // Return true if the message should be rebroadcasted.
+  pub async fn handle_message(&self, msg: &[u8]) -> bool {
+    match msg.first() {
+      Some(&TRANSACTION_MESSAGE) => {
+        let Ok(tx) = Transaction::read::<&[u8]>(&mut &msg[1 ..]) else {
+          log::error!("received invalid transaction message");
+          return false;
+        };
+
+        // TODO: Sync mempools with fellow peers
+        // Can we just rebroadcast transactions not included for at least two blocks?
+        let res =
+          self.network.blockchain.write().await.add_transaction::<TendermintNetwork<D, T, P>>(
+            false,
+            tx,
+            &self.network.signature_scheme(),
+          );
+        log::debug!("received transaction message. valid new transaction: {res:?}");
+        res == Ok(true)
+      }
+
+      Some(&TENDERMINT_MESSAGE) => {
+        let Ok(msg) =
+          SignedMessageFor::<TendermintNetwork<D, T, P>>::decode::<&[u8]>(&mut &msg[1 ..])
+        else {
+          log::error!("received invalid tendermint message");
+          return false;
+        };
+
+        self.messages.write().await.send(msg).await.unwrap();
+        false
+      }
+
+      _ => false,
+    }
+  }
+
+  /// Get a Future which will resolve once the next block has been added.
+  pub async fn next_block_notification(
+    &self,
+  ) -> impl Send + Sync + core::future::Future<Output = Result<(), impl Send + Sync>> {
+    let (tx, rx) = tokio::sync::oneshot::channel();
+    self.network.blockchain.write().await.next_block_notifications.push_back(tx);
+    rx
+  }
+}
+
+#[derive(Clone)]
+pub struct TributaryReader<D: Db, T: TransactionTrait>(D, [u8; 32], PhantomData<T>);
+impl<D: Db, T: TransactionTrait> TributaryReader<D, T> {
+  pub fn genesis(&self) -> [u8; 32] {
+    self.1
+  }
+
+  // Since these values are static once set, they can be safely read from the database without lock
+  // acquisition
+  pub fn block(&self, hash: &[u8; 32]) -> Option<Block<T>> {
+    Blockchain::<D, T>::block_from_db(&self.0, self.1, hash)
+  }
+  pub fn commit(&self, hash: &[u8; 32]) -> Option<Vec<u8>> {
+    Blockchain::<D, T>::commit_from_db(&self.0, self.1, hash)
+  }
+  pub fn parsed_commit(&self, hash: &[u8; 32]) -> Option<Commit<Validators>> {
+    self.commit(hash).map(|commit| Commit::<Validators>::decode(&mut commit.as_ref()).unwrap())
+  }
+  pub fn block_after(&self, hash: &[u8; 32]) -> Option<[u8; 32]> {
+    Blockchain::<D, T>::block_after(&self.0, self.1, hash)
+  }
+  pub fn time_of_block(&self, hash: &[u8; 32]) -> Option<u64> {
+    self
+      .commit(hash)
+      .map(|commit| Commit::<Validators>::decode(&mut commit.as_ref()).unwrap().end_time)
+  }
+
+  pub fn locally_provided_txs_in_block(&self, hash: &[u8; 32], order: &str) -> bool {
+    Blockchain::<D, T>::locally_provided_txs_in_block(&self.0, &self.1, hash, order)
+  }
+
+  // This isn't static, yet can be read with only minor discrepancy risks
+  pub fn tip(&self) -> [u8; 32] {
+    Blockchain::<D, T>::tip_from_db(&self.0, self.1)
+  }
+}

coordinator/tributary-sdk/src/transaction.rs

@@ -0,0 +1,218 @@
+use core::fmt::Debug;
+use std::io;
+
+use zeroize::Zeroize;
+use thiserror::Error;
+
+use blake2::{Digest, Blake2b512};
+
+use ciphersuite::{
+  group::{Group, GroupEncoding},
+  Ciphersuite, Ristretto,
+};
+use schnorr::SchnorrSignature;
+
+use crate::{TRANSACTION_SIZE_LIMIT, ReadWrite};
+
+#[derive(Clone, PartialEq, Eq, Debug, Error)]
+pub enum TransactionError {
+  /// Transaction exceeded the size limit.
+  #[error("transaction is too large")]
+  TooLargeTransaction,
+  /// Transaction's signer isn't a participant.
+  #[error("invalid signer")]
+  InvalidSigner,
+  /// Transaction's nonce isn't the prior nonce plus one.
+  #[error("invalid nonce")]
+  InvalidNonce,
+  /// Transaction's signature is invalid.
+  #[error("invalid signature")]
+  InvalidSignature,
+  /// Transaction's content is invalid.
+  #[error("transaction content is invalid")]
+  InvalidContent,
+  /// Transaction's signer has too many transactions in the mempool.
+  #[error("signer has too many transactions in the mempool")]
+  TooManyInMempool,
+  /// Provided Transaction added to mempool.
+  #[error("provided transaction added to mempool")]
+  ProvidedAddedToMempool,
+}
+
+/// Data for a signed transaction.
+#[derive(Clone, PartialEq, Eq, Debug)]
+pub struct Signed {
+  pub signer: <Ristretto as Ciphersuite>::G,
+  pub nonce: u32,
+  pub signature: SchnorrSignature<Ristretto>,
+}
+
+impl ReadWrite for Signed {
+  fn read<R: io::Read>(reader: &mut R) -> io::Result<Self> {
+    let signer = Ristretto::read_G(reader)?;
+
+    let mut nonce = [0; 4];
+    reader.read_exact(&mut nonce)?;
+    let nonce = u32::from_le_bytes(nonce);
+    if nonce >= (u32::MAX - 1) {
+      Err(io::Error::other("nonce exceeded limit"))?;
+    }
+
+    let mut signature = SchnorrSignature::<Ristretto>::read(reader)?;
+    if signature.R.is_identity().into() {
+      // Anyone malicious could remove this and try to find zero signatures
+      // We should never produce zero signatures though meaning this should never come up
+      // If it does somehow come up, this is a decent courtesy
+      signature.zeroize();
+      Err(io::Error::other("signature nonce was identity"))?;
+    }
+
+    Ok(Signed { signer, nonce, signature })
+  }
+
+  fn write<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
+    // This is either an invalid signature or a private key leak
+    if self.signature.R.is_identity().into() {
+      Err(io::Error::other("signature nonce was identity"))?;
+    }
+    writer.write_all(&self.signer.to_bytes())?;
+    writer.write_all(&self.nonce.to_le_bytes())?;
+    self.signature.write(writer)
+  }
+}
+
+impl Signed {
+  pub fn read_without_nonce<R: io::Read>(reader: &mut R, nonce: u32) -> io::Result<Self> {
+    let signer = Ristretto::read_G(reader)?;
+
+    let mut signature = SchnorrSignature::<Ristretto>::read(reader)?;
+    if signature.R.is_identity().into() {
+      // Anyone malicious could remove this and try to find zero signatures
+      // We should never produce zero signatures though meaning this should never come up
+      // If it does somehow come up, this is a decent courtesy
+      signature.zeroize();
+      Err(io::Error::other("signature nonce was identity"))?;
+    }
+
+    Ok(Signed { signer, nonce, signature })
+  }
+
+  pub fn write_without_nonce<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
+    // This is either an invalid signature or a private key leak
+    if self.signature.R.is_identity().into() {
+      Err(io::Error::other("signature nonce was identity"))?;
+    }
+    writer.write_all(&self.signer.to_bytes())?;
+    self.signature.write(writer)
+  }
+}
+
+#[allow(clippy::large_enum_variant)]
+#[derive(Clone, PartialEq, Eq, Debug)]
+pub enum TransactionKind {
+  /// This transaction should be provided by every validator, in an exact order.
+  ///
+  /// The contained static string names the orderer to use. This allows two distinct provided
+  /// transaction kinds, without a synchronized order, to be ordered within their own kind without
+  /// requiring ordering with each other.
+  ///
+  /// The only malleability is in when this transaction appears on chain. The block producer will
+  /// include it when they have it. Block verification will fail for validators without it.
+  ///
+  /// If a supermajority of validators produce a commit for a block with a provided transaction
+  /// which isn't locally held, the block will be added to the local chain. When the transaction is
+  /// locally provided, it will be compared for correctness to the on-chain version
+  ///
+  /// In order to ensure TXs aren't accidentally provided multiple times, all provided transactions
+  /// must have a unique hash which is also unique to all Unsigned transactions.
+  Provided(&'static str),
+
+  /// An unsigned transaction, only able to be included by the block producer.
+  ///
+  /// Once an Unsigned transaction is included on-chain, it may not be included again. In order to
+  /// have multiple Unsigned transactions with the same values included on-chain, some distinct
+  /// nonce must be included in order to cause a distinct hash.
+  ///
+  /// The hash must also be unique with all Provided transactions.
+  Unsigned,
+
+  /// A signed transaction.
+  Signed(Vec<u8>, Signed),
+}
+
+// TODO: Should this be renamed TransactionTrait now that a literal Transaction exists?
+// Or should the literal Transaction be renamed to Event?
+pub trait Transaction: 'static + Send + Sync + Clone + Eq + Debug + ReadWrite {
+  /// Return what type of transaction this is.
+  fn kind(&self) -> TransactionKind;
+
+  /// Return the hash of this transaction.
+  ///
+  /// The hash must NOT commit to the signature.
+  fn hash(&self) -> [u8; 32];
+
+  /// Perform transaction-specific verification.
+  fn verify(&self) -> Result<(), TransactionError>;
+
+  /// Obtain the challenge for this transaction's signature.
+  ///
+  /// Do not override this unless you know what you're doing.
+  ///
+  /// Panics if called on non-signed transactions.
+  fn sig_hash(&self, genesis: [u8; 32]) -> <Ristretto as Ciphersuite>::F {
+    match self.kind() {
+      TransactionKind::Signed(order, Signed { signature, .. }) => {
+        <Ristretto as Ciphersuite>::F::from_bytes_mod_order_wide(
+          &Blake2b512::digest(
+            [
+              b"Tributary Signed Transaction",
+              genesis.as_ref(),
+              &self.hash(),
+              order.as_ref(),
+              signature.R.to_bytes().as_ref(),
+            ]
+            .concat(),
+          )
+          .into(),
+        )
+      }
+      _ => panic!("sig_hash called on non-signed transaction"),
+    }
+  }
+}
+
+pub trait GAIN: FnMut(&<Ristretto as Ciphersuite>::G, &[u8]) -> Option<u32> {}
+impl<F: FnMut(&<Ristretto as Ciphersuite>::G, &[u8]) -> Option<u32>> GAIN for F {}
+
+pub(crate) fn verify_transaction<F: GAIN, T: Transaction>(
+  tx: &T,
+  genesis: [u8; 32],
+  get_and_increment_nonce: &mut F,
+) -> Result<(), TransactionError> {
+  if tx.serialize().len() > TRANSACTION_SIZE_LIMIT {
+    Err(TransactionError::TooLargeTransaction)?;
+  }
+
+  tx.verify()?;
+
+  match tx.kind() {
+    TransactionKind::Provided(_) | TransactionKind::Unsigned => {}
+    TransactionKind::Signed(order, Signed { signer, nonce, signature }) => {
+      if let Some(next_nonce) = get_and_increment_nonce(&signer, &order) {
+        if nonce != next_nonce {
+          Err(TransactionError::InvalidNonce)?;
+        }
+      } else {
+        // Not a participant
+        Err(TransactionError::InvalidSigner)?;
+      }
+
+      // TODO: Use a batch verification here
+      if !signature.verify(signer, tx.sig_hash(genesis)) {
+        Err(TransactionError::InvalidSignature)?;
+      }
+    }
+  }
+
+  Ok(())
+}

coordinator/tributary/Cargo.toml

@@ -1,11 +1,13 @@
 [package]
-name = "tributary-chain"
+name = "serai-coordinator-tributary"
 version = "0.1.0"
-description = "A micro-blockchain to provide consensus and ordering to P2P communication"
+description = "The Tributary used by the Serai Coordinator"
 license = "AGPL-3.0-only"
 repository = "https://github.com/serai-dex/serai/tree/develop/coordinator/tributary"
 authors = ["Luke Parker <lukeparker5132@gmail.com>"]
+keywords = []
 edition = "2021"
+publish = false
 rust-version = "1.81"
 
 [package.metadata.docs.rs]
@@ -16,34 +18,29 @@ rustdoc-args = ["--cfg", "docsrs"]
 workspace = true
 
 [dependencies]
-thiserror = { version = "2", default-features = false, features = ["std"] }
-
-subtle = { version = "^2", default-features = false, features = ["std"] }
 zeroize = { version = "^1.5", default-features = false, features = ["std"] }
-
-rand = { version = "0.8", default-features = false, features = ["std"] }
-rand_chacha = { version = "0.3", default-features = false, features = ["std"] }
+rand_core = { version = "0.6", default-features = false, features = ["std"] }
 
 blake2 = { version = "0.10", default-features = false, features = ["std"] }
-transcript = { package = "flexible-transcript", path = "../../crypto/transcript", default-features = false, features = ["std", "recommended"] }
-
-ciphersuite = { package = "ciphersuite", path = "../../crypto/ciphersuite", default-features = false, features = ["std", "ristretto"] }
+ciphersuite = { path = "../../crypto/ciphersuite", default-features = false, features = ["std"] }
 schnorr = { package = "schnorr-signatures", path = "../../crypto/schnorr", default-features = false, features = ["std"] }
 
-hex = { version = "0.4", default-features = false, features = ["std"] }
-log = { version = "0.4", default-features = false, features = ["std"] }
+scale = { package = "parity-scale-codec", version = "3", default-features = false, features = ["std", "derive"] }
+borsh = { version = "1", default-features = false, features = ["std", "derive", "de_strict_order"] }
+
+serai-client = { path = "../../substrate/client", default-features = false, features = ["serai", "borsh"] }
 
 serai-db = { path = "../../common/db" }
+serai-task = { path = "../../common/task", version = "0.1" }
 
-scale = { package = "parity-scale-codec", version = "3", default-features = false, features = ["std", "derive"] }
-futures-util = { version = "0.3", default-features = false, features = ["std", "sink", "channel"] }
-futures-channel = { version = "0.3", default-features = false, features = ["std", "sink"] }
-tendermint = { package = "tendermint-machine", path = "./tendermint" }
+tributary-sdk = { path = "../tributary-sdk" }
 
-tokio = { version = "1", default-features = false, features = ["sync", "time", "rt"] }
+serai-cosign = { path = "../cosign" }
+serai-coordinator-substrate = { path = "../substrate" }
 
-[dev-dependencies]
-tokio = { version = "1", features = ["macros"] }
+messages = { package = "serai-processor-messages", path = "../../processor/messages" }
+
+log = { version = "0.4", default-features = false, features = ["std"] }
 
 [features]
-tests = []
+longer-reattempts = []

coordinator/tributary/LICENSE

@@ -1,6 +1,6 @@
 AGPL-3.0-only license
 
-Copyright (c) 2023 Luke Parker
+Copyright (c) 2023-2025 Luke Parker
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU Affero General Public License Version 3 as

coordinator/tributary/README.md

@@ -1,3 +1,4 @@
-# Tributary
+# Serai Coordinator Tributary
 
-A verifiable, ordered broadcast layer implemented as a BFT micro-blockchain.
+The Tributary used by the Serai Coordinator. This includes the `Transaction`
+definition and the code to handle blocks added on-chain.

coordinator/tributary/src/db.rs

@@ -9,7 +9,9 @@ use messages::sign::{VariantSignId, SignId};
 
 use serai_db::*;
 
-use crate::tributary::transaction::SigningProtocolRound;
+use serai_cosign::CosignIntent;
+
+use crate::transaction::SigningProtocolRound;
 
 /// A topic within the database which the group participates in
 #[derive(Clone, Copy, PartialEq, Eq, Debug, Encode, BorshSerialize, BorshDeserialize)]
@@ -167,6 +169,9 @@ impl Topic {
   }
 }
 
+pub(crate) trait Borshy: BorshSerialize + BorshDeserialize {}
+impl<T: BorshSerialize + BorshDeserialize> Borshy for T {}
+
 /// The resulting data set from an accumulation
 pub(crate) enum DataSet<D: Borshy> {
   /// Accumulating this did not produce a data set to act on
@@ -176,21 +181,25 @@ pub(crate) enum DataSet<D: Borshy> {
   Participating(HashMap<SeraiAddress, D>),
 }
 
-trait Borshy: BorshSerialize + BorshDeserialize {}
-impl<T: BorshSerialize + BorshDeserialize> Borshy for T {}
-
 create_db!(
   CoordinatorTributary {
     // The last handled tributary block's (number, hash)
     LastHandledTributaryBlock: (set: ValidatorSet) -> (u64, [u8; 32]),
 
-    // The slash points a validator has accrued, with u64::MAX representing a fatal slash.
-    SlashPoints: (set: ValidatorSet, validator: SeraiAddress) -> u64,
+    // The slash points a validator has accrued, with u32::MAX representing a fatal slash.
+    SlashPoints: (set: ValidatorSet, validator: SeraiAddress) -> u32,
 
+    // The cosign intent for a Substrate block
+    CosignIntents: (set: ValidatorSet, substrate_block_hash: [u8; 32]) -> CosignIntent,
     // The latest Substrate block to cosign.
     LatestSubstrateBlockToCosign: (set: ValidatorSet) -> [u8; 32],
-    // If we're actively cosigning or not.
-    ActivelyCosigning: (set: ValidatorSet) -> (),
+    // The hash of the block we're actively cosigning.
+    ActivelyCosigning: (set: ValidatorSet) -> [u8; 32],
+    // If this block has already been cosigned.
+    Cosigned: (set: ValidatorSet, substrate_block_hash: [u8; 32]) -> (),
+
+    // The plans to whitelist upon a `Transaction::SubstrateBlock` being included on-chain.
+    SubstrateBlockPlans: (set: ValidatorSet, substrate_block_hash: [u8; 32]) -> Vec<[u8; 32]>,
 
     // The weight accumulated for a topic.
     AccumulatedWeight: (set: ValidatorSet, topic: Topic) -> u64,
@@ -238,19 +247,20 @@ impl TributaryDb {
   ) {
     LatestSubstrateBlockToCosign::set(txn, set, &substrate_block_hash);
   }
-  pub(crate) fn actively_cosigning(txn: &mut impl DbTxn, set: ValidatorSet) -> bool {
-    ActivelyCosigning::get(txn, set).is_some()
+  pub(crate) fn actively_cosigning(txn: &mut impl DbTxn, set: ValidatorSet) -> Option<[u8; 32]> {
+    ActivelyCosigning::get(txn, set)
   }
   pub(crate) fn start_cosigning(
     txn: &mut impl DbTxn,
     set: ValidatorSet,
+    substrate_block_hash: [u8; 32],
     substrate_block_number: u64,
   ) {
     assert!(
       ActivelyCosigning::get(txn, set).is_none(),
       "starting cosigning while already cosigning"
     );
-    ActivelyCosigning::set(txn, set, &());
+    ActivelyCosigning::set(txn, set, &substrate_block_hash);
 
     TributaryDb::recognize_topic(
       txn,
@@ -265,6 +275,20 @@ impl TributaryDb {
   pub(crate) fn finish_cosigning(txn: &mut impl DbTxn, set: ValidatorSet) {
     assert!(ActivelyCosigning::take(txn, set).is_some(), "finished cosigning but not cosigning");
   }
+  pub(crate) fn mark_cosigned(
+    txn: &mut impl DbTxn,
+    set: ValidatorSet,
+    substrate_block_hash: [u8; 32],
+  ) {
+    Cosigned::set(txn, set, substrate_block_hash, &());
+  }
+  pub(crate) fn cosigned(
+    txn: &mut impl DbTxn,
+    set: ValidatorSet,
+    substrate_block_hash: [u8; 32],
+  ) -> bool {
+    Cosigned::get(txn, set, substrate_block_hash).is_some()
+  }
 
   pub(crate) fn recognize_topic(txn: &mut impl DbTxn, set: ValidatorSet, topic: Topic) {
     AccumulatedWeight::set(txn, set, topic, &0);
@@ -272,7 +296,19 @@ impl TributaryDb {
 
   pub(crate) fn start_of_block(txn: &mut impl DbTxn, set: ValidatorSet, block_number: u64) {
     for topic in Reattempt::take(txn, set, block_number).unwrap_or(vec![]) {
-      // TODO: Slash all people who preprocessed but didn't share
+      /*
+        TODO: Slash all people who preprocessed but didn't share, and add a delay to their
+        participations in future protocols. When we call accumulate, if the participant has no
+        delay, their accumulation occurs immediately. Else, the accumulation occurs after the
+        specified delay.
+
+        This means even if faulty validators are first to preprocess, they won't be selected for
+        the signing set unless there's a lack of less faulty validators available.
+
+        We need to decrease this delay upon successful partipations, and set it to the maximum upon
+        `f + 1` validators voting to fatally slash the validator in question. This won't issue the
+        fatal slash but should still be effective.
+      */
       Self::recognize_topic(txn, set, topic);
       if let Some(id) = topic.sign_id(set) {
         Self::send_message(txn, set, messages::sign::CoordinatorMessage::Reattempt { id });
@@ -287,7 +323,7 @@ impl TributaryDb {
     reason: &str,
   ) {
     log::warn!("{validator} fatally slashed: {reason}");
-    SlashPoints::set(txn, set, validator, &u64::MAX);
+    SlashPoints::set(txn, set, validator, &u32::MAX);
   }
 
   pub(crate) fn is_fatally_slashed(
@@ -295,7 +331,7 @@ impl TributaryDb {
     set: ValidatorSet,
     validator: SeraiAddress,
   ) -> bool {
-    SlashPoints::get(getter, set, validator).unwrap_or(0) == u64::MAX
+    SlashPoints::get(getter, set, validator).unwrap_or(0) == u32::MAX
   }
 
   #[allow(clippy::too_many_arguments)]
@@ -360,12 +396,12 @@ impl TributaryDb {
         // 5 minutes
         #[cfg(not(feature = "longer-reattempts"))]
         const BASE_REATTEMPT_DELAY: u32 =
-          (5u32 * 60 * 1000).div_ceil(tributary::tendermint::TARGET_BLOCK_TIME);
+          (5u32 * 60 * 1000).div_ceil(tributary_sdk::tendermint::TARGET_BLOCK_TIME);
 
         // 10 minutes, intended for latent environments like the GitHub CI
         #[cfg(feature = "longer-reattempts")]
         const BASE_REATTEMPT_DELAY: u32 =
-          (10u32 * 60 * 1000).div_ceil(tributary::tendermint::TARGET_BLOCK_TIME);
+          (10u32 * 60 * 1000).div_ceil(tributary_sdk::tendermint::TARGET_BLOCK_TIME);
 
         // Linearly scale the time for the protocol with the attempt number
         let blocks_till_reattempt = u64::from(attempt * BASE_REATTEMPT_DELAY);

coordinator/tributary/src/lib.rs

@@ -1,388 +1,584 @@
-use core::{marker::PhantomData, fmt::Debug, future::Future};
-use std::{sync::Arc, io};
+#![cfg_attr(docsrs, feature(doc_auto_cfg))]
+#![doc = include_str!("../README.md")]
+#![deny(missing_docs)]
 
-use zeroize::Zeroizing;
+use core::{marker::PhantomData, future::Future};
+use std::collections::HashMap;
 
-use ciphersuite::{Ciphersuite, Ristretto};
+use ciphersuite::group::GroupEncoding;
 
-use scale::Decode;
-use futures_channel::mpsc::UnboundedReceiver;
-use futures_util::{StreamExt, SinkExt};
-use ::tendermint::{
-  ext::{BlockNumber, Commit, Block as BlockTrait, Network},
-  SignedMessageFor, SyncedBlock, SyncedBlockSender, SyncedBlockResultReceiver, MessageSender,
-  TendermintMachine, TendermintHandle,
+use serai_client::{
+  primitives::SeraiAddress,
+  validator_sets::primitives::{ValidatorSet, Slash},
 };
 
-pub use ::tendermint::Evidence;
+use serai_db::*;
+use serai_task::ContinuallyRan;
 
-use serai_db::Db;
+use tributary_sdk::{
+  tendermint::{
+    tx::{TendermintTx, Evidence, decode_signed_message},
+    TendermintNetwork,
+  },
+  Signed as TributarySigned, TransactionKind, TransactionTrait,
+  Transaction as TributaryTransaction, Block, TributaryReader, P2p,
+};
 
-use tokio::sync::RwLock;
+use serai_cosign::CosignIntent;
+use serai_coordinator_substrate::NewSetInformation;
 
-mod merkle;
-pub(crate) use merkle::*;
+use messages::sign::VariantSignId;
 
-pub mod transaction;
-pub use transaction::{TransactionError, Signed, TransactionKind, Transaction as TransactionTrait};
+mod transaction;
+pub use transaction::{SigningProtocolRound, Signed, Transaction};
 
-use crate::tendermint::tx::TendermintTx;
+mod db;
+use db::*;
 
-mod provided;
-pub(crate) use provided::*;
-pub use provided::ProvidedError;
-
-mod block;
-pub use block::*;
-
-mod blockchain;
-pub(crate) use blockchain::*;
-
-mod mempool;
-pub(crate) use mempool::*;
-
-pub mod tendermint;
-pub(crate) use crate::tendermint::*;
-
-#[cfg(any(test, feature = "tests"))]
-pub mod tests;
-
-/// Size limit for an individual transaction.
-// This needs to be big enough to participate in a 101-of-150 eVRF DKG with each element taking
-// `MAX_KEY_LEN`. This also needs to be big enough to pariticpate in signing 520 Bitcoin inputs
-// with 49 key shares, and signing 120 Monero inputs with 49 key shares.
-// TODO: Add a test for these properties
-pub const TRANSACTION_SIZE_LIMIT: usize = 2_000_000;
-/// Amount of transactions a single account may have in the mempool.
-pub const ACCOUNT_MEMPOOL_LIMIT: u32 = 50;
-/// Block size limit.
-// This targets a growth limit of roughly 30 GB a day, under load, in order to prevent a malicious
-// participant from flooding disks and causing out of space errors in order processes.
-pub const BLOCK_SIZE_LIMIT: usize = 2_001_000;
-
-pub(crate) const TENDERMINT_MESSAGE: u8 = 0;
-pub(crate) const TRANSACTION_MESSAGE: u8 = 1;
-
-#[allow(clippy::large_enum_variant)]
-#[derive(Clone, PartialEq, Eq, Debug)]
-pub enum Transaction<T: TransactionTrait> {
-  Tendermint(TendermintTx),
-  Application(T),
-}
-
-impl<T: TransactionTrait> ReadWrite for Transaction<T> {
-  fn read<R: io::Read>(reader: &mut R) -> io::Result<Self> {
-    let mut kind = [0];
-    reader.read_exact(&mut kind)?;
-    match kind[0] {
-      0 => {
-        let tx = TendermintTx::read(reader)?;
-        Ok(Transaction::Tendermint(tx))
-      }
-      1 => {
-        let tx = T::read(reader)?;
-        Ok(Transaction::Application(tx))
-      }
-      _ => Err(io::Error::other("invalid transaction type")),
-    }
-  }
-  fn write<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
-    match self {
-      Transaction::Tendermint(tx) => {
-        writer.write_all(&[0])?;
-        tx.write(writer)
-      }
-      Transaction::Application(tx) => {
-        writer.write_all(&[1])?;
-        tx.write(writer)
-      }
-    }
+/// Messages to send to the Processors.
+pub struct ProcessorMessages;
+impl ProcessorMessages {
+  /// Try to receive a message to send to a Processor.
+  pub fn try_recv(txn: &mut impl DbTxn, set: ValidatorSet) -> Option<messages::CoordinatorMessage> {
+    db::ProcessorMessages::try_recv(txn, set)
   }
 }
 
-impl<T: TransactionTrait> Transaction<T> {
-  pub fn hash(&self) -> [u8; 32] {
-    match self {
-      Transaction::Tendermint(tx) => tx.hash(),
-      Transaction::Application(tx) => tx.hash(),
-    }
-  }
-
-  pub fn kind(&self) -> TransactionKind {
-    match self {
-      Transaction::Tendermint(tx) => tx.kind(),
-      Transaction::Application(tx) => tx.kind(),
-    }
-  }
-}
-
-/// An item which can be read and written.
-pub trait ReadWrite: Sized {
-  fn read<R: io::Read>(reader: &mut R) -> io::Result<Self>;
-  fn write<W: io::Write>(&self, writer: &mut W) -> io::Result<()>;
-
-  fn serialize(&self) -> Vec<u8> {
-    // BlockHeader is 64 bytes and likely the smallest item in this system
-    let mut buf = Vec::with_capacity(64);
-    self.write(&mut buf).unwrap();
-    buf
-  }
-}
-
-pub trait P2p: 'static + Send + Sync + Clone {
-  /// Broadcast a message to all other members of the Tributary with the specified genesis.
+/// The cosign intents.
+pub struct CosignIntents;
+impl CosignIntents {
+  /// Provide a CosignIntent for this Tributary.
   ///
-  /// The Tributary will re-broadcast consensus messages on a fixed interval to ensure they aren't
-  /// prematurely dropped from the P2P layer. THe P2P layer SHOULD perform content-based
-  /// deduplication to ensure a sane amount of load.
-  fn broadcast(&self, genesis: [u8; 32], msg: Vec<u8>) -> impl Send + Future<Output = ()>;
+  /// This must be done before the associated `Transaction::Cosign` is provided.
+  pub fn provide(txn: &mut impl DbTxn, set: ValidatorSet, intent: &CosignIntent) {
+    db::CosignIntents::set(txn, set, intent.block_hash, intent);
   }
-
-impl<P: P2p> P2p for Arc<P> {
-  fn broadcast(&self, genesis: [u8; 32], msg: Vec<u8>) -> impl Send + Future<Output = ()> {
-    P::broadcast(self, genesis, msg)
+  fn take(
+    txn: &mut impl DbTxn,
+    set: ValidatorSet,
+    substrate_block_hash: [u8; 32],
+  ) -> Option<CosignIntent> {
+    db::CosignIntents::take(txn, set, substrate_block_hash)
   }
 }
 
-#[derive(Clone)]
-pub struct Tributary<D: Db, T: TransactionTrait, P: P2p> {
-  db: D,
-
-  genesis: [u8; 32],
-  network: TendermintNetwork<D, T, P>,
-
-  synced_block: Arc<RwLock<SyncedBlockSender<TendermintNetwork<D, T, P>>>>,
-  synced_block_result: Arc<RwLock<SyncedBlockResultReceiver>>,
-  messages: Arc<RwLock<MessageSender<TendermintNetwork<D, T, P>>>>,
+/// The plans to whitelist upon a `Transaction::SubstrateBlock` being included on-chain.
+pub struct SubstrateBlockPlans;
+impl SubstrateBlockPlans {
+  /// Set the plans to whitelist upon the associated `Transaction::SubstrateBlock` being included
+  /// on-chain.
+  ///
+  /// This must be done before the associated `Transaction::Cosign` is provided.
+  pub fn set(
+    txn: &mut impl DbTxn,
+    set: ValidatorSet,
+    substrate_block_hash: [u8; 32],
+    plans: &Vec<[u8; 32]>,
+  ) {
+    db::SubstrateBlockPlans::set(txn, set, substrate_block_hash, &plans);
+  }
+  fn take(
+    txn: &mut impl DbTxn,
+    set: ValidatorSet,
+    substrate_block_hash: [u8; 32],
+  ) -> Option<Vec<[u8; 32]>> {
+    db::SubstrateBlockPlans::take(txn, set, substrate_block_hash)
+  }
 }
 
-impl<D: Db, T: TransactionTrait, P: P2p> Tributary<D, T, P> {
-  pub async fn new(
-    db: D,
-    genesis: [u8; 32],
-    start_time: u64,
-    key: Zeroizing<<Ristretto as Ciphersuite>::F>,
-    validators: Vec<(<Ristretto as Ciphersuite>::G, u64)>,
-    p2p: P,
-  ) -> Option<Self> {
-    log::info!("new Tributary with genesis {}", hex::encode(genesis));
-
-    let validators_vec = validators.iter().map(|validator| validator.0).collect::<Vec<_>>();
-
-    let signer = Arc::new(Signer::new(genesis, key));
-    let validators = Arc::new(Validators::new(genesis, validators)?);
-
-    let mut blockchain = Blockchain::new(db.clone(), genesis, &validators_vec);
-    let block_number = BlockNumber(blockchain.block_number());
-
-    let start_time = if let Some(commit) = blockchain.commit(&blockchain.tip()) {
-      Commit::<Validators>::decode(&mut commit.as_ref()).unwrap().end_time
-    } else {
-      start_time
-    };
-    let proposal = TendermintBlock(
-      blockchain.build_block::<TendermintNetwork<D, T, P>>(&validators).serialize(),
-    );
-    let blockchain = Arc::new(RwLock::new(blockchain));
-
-    let network = TendermintNetwork { genesis, signer, validators, blockchain, p2p };
-
-    let TendermintHandle { synced_block, synced_block_result, messages, machine } =
-      TendermintMachine::new(
-        db.clone(),
-        network.clone(),
-        genesis,
-        block_number,
-        start_time,
-        proposal,
-      )
-      .await;
-    tokio::spawn(machine.run());
-
-    Some(Self {
-      db,
-      genesis,
-      network,
-      synced_block: Arc::new(RwLock::new(synced_block)),
-      synced_block_result: Arc::new(RwLock::new(synced_block_result)),
-      messages: Arc::new(RwLock::new(messages)),
-    })
+struct ScanBlock<'a, TD: Db, TDT: DbTxn, P: P2p> {
+  _td: PhantomData<TD>,
+  _p2p: PhantomData<P>,
+  tributary_txn: &'a mut TDT,
+  set: ValidatorSet,
+  validators: &'a [SeraiAddress],
+  total_weight: u64,
+  validator_weights: &'a HashMap<SeraiAddress, u64>,
+}
+impl<'a, TD: Db, TDT: DbTxn, P: P2p> ScanBlock<'a, TD, TDT, P> {
+  fn potentially_start_cosign(&mut self) {
+    // Don't start a new cosigning instance if we're actively running one
+    if TributaryDb::actively_cosigning(self.tributary_txn, self.set).is_some() {
+      return;
     }
 
-  pub fn block_time() -> u32 {
-    TendermintNetwork::<D, T, P>::block_time()
-  }
-
-  pub fn genesis(&self) -> [u8; 32] {
-    self.genesis
-  }
-
-  pub async fn block_number(&self) -> u64 {
-    self.network.blockchain.read().await.block_number()
-  }
-  pub async fn tip(&self) -> [u8; 32] {
-    self.network.blockchain.read().await.tip()
-  }
-
-  pub fn reader(&self) -> TributaryReader<D, T> {
-    TributaryReader(self.db.clone(), self.genesis, PhantomData)
-  }
-
-  pub async fn provide_transaction(&self, tx: T) -> Result<(), ProvidedError> {
-    self.network.blockchain.write().await.provide_transaction(tx)
-  }
-
-  pub async fn next_nonce(
-    &self,
-    signer: &<Ristretto as Ciphersuite>::G,
-    order: &[u8],
-  ) -> Option<u32> {
-    self.network.blockchain.read().await.next_nonce(signer, order)
-  }
-
-  // Returns Ok(true) if new, Ok(false) if an already present unsigned, or the error.
-  // Safe to be &self since the only meaningful usage of self is self.network.blockchain which
-  // successfully acquires its own write lock
-  pub async fn add_transaction(&self, tx: T) -> Result<bool, TransactionError> {
-    let tx = Transaction::Application(tx);
-    let mut to_broadcast = vec![TRANSACTION_MESSAGE];
-    tx.write(&mut to_broadcast).unwrap();
-    let res = self.network.blockchain.write().await.add_transaction::<TendermintNetwork<D, T, P>>(
-      true,
-      tx,
-      &self.network.signature_scheme(),
-    );
-    if res == Ok(true) {
-      self.network.p2p.broadcast(self.genesis, to_broadcast).await;
-    }
-    res
-  }
-
-  async fn sync_block_internal(
-    &self,
-    block: Block<T>,
-    commit: Vec<u8>,
-    result: &mut UnboundedReceiver<bool>,
-  ) -> bool {
-    let (tip, block_number) = {
-      let blockchain = self.network.blockchain.read().await;
-      (blockchain.tip(), blockchain.block_number())
-    };
-
-    if block.header.parent != tip {
-      log::debug!("told to sync a block whose parent wasn't our tip");
-      return false;
-    }
-
-    let block = TendermintBlock(block.serialize());
-    let mut commit_ref = commit.as_ref();
-    let Ok(commit) = Commit::<Arc<Validators>>::decode(&mut commit_ref) else {
-      log::error!("sent an invalidly serialized commit");
-      return false;
-    };
-    // Storage DoS vector. We *could* truncate to solely the relevant portion, trying to save this,
-    // yet then we'd have to test the truncation was performed correctly.
-    if !commit_ref.is_empty() {
-      log::error!("sent an commit with additional data after it");
-      return false;
-    }
-    if !self.network.verify_commit(block.id(), &commit) {
-      log::error!("sent an invalid commit");
-      return false;
-    }
-
-    let number = BlockNumber(block_number + 1);
-    self.synced_block.write().await.send(SyncedBlock { number, block, commit }).await.unwrap();
-    result.next().await.unwrap()
-  }
-
-  // Sync a block.
-  // TODO: Since we have a static validator set, we should only need the tail commit?
-  pub async fn sync_block(&self, block: Block<T>, commit: Vec<u8>) -> bool {
-    let mut result = self.synced_block_result.write().await;
-    self.sync_block_internal(block, commit, &mut result).await
-  }
-
-  // Return true if the message should be rebroadcasted.
-  pub async fn handle_message(&self, msg: &[u8]) -> bool {
-    match msg.first() {
-      Some(&TRANSACTION_MESSAGE) => {
-        let Ok(tx) = Transaction::read::<&[u8]>(&mut &msg[1 ..]) else {
-          log::error!("received invalid transaction message");
-          return false;
-        };
-
-        // TODO: Sync mempools with fellow peers
-        // Can we just rebroadcast transactions not included for at least two blocks?
-        let res =
-          self.network.blockchain.write().await.add_transaction::<TendermintNetwork<D, T, P>>(
-            false,
-            tx,
-            &self.network.signature_scheme(),
-          );
-        log::debug!("received transaction message. valid new transaction: {res:?}");
-        res == Ok(true)
-      }
-
-      Some(&TENDERMINT_MESSAGE) => {
-        let Ok(msg) =
-          SignedMessageFor::<TendermintNetwork<D, T, P>>::decode::<&[u8]>(&mut &msg[1 ..])
+    // Fetch the latest intended-to-be-cosigned block
+    let Some(latest_substrate_block_to_cosign) =
+      TributaryDb::latest_substrate_block_to_cosign(self.tributary_txn, self.set)
     else {
-          log::error!("received invalid tendermint message");
-          return false;
+      return;
     };
 
-        self.messages.write().await.send(msg).await.unwrap();
-        false
+    // If it was already cosigned, return
+    if TributaryDb::cosigned(self.tributary_txn, self.set, latest_substrate_block_to_cosign) {
+      return;
     }
 
-      _ => false,
+    let intent =
+      CosignIntents::take(self.tributary_txn, self.set, latest_substrate_block_to_cosign)
+        .expect("Transaction::Cosign locally provided but CosignIntents wasn't populated");
+    assert_eq!(
+      intent.block_hash, latest_substrate_block_to_cosign,
+      "provided CosignIntent wasn't saved by its block hash"
+    );
+
+    // Mark us as actively cosigning
+    TributaryDb::start_cosigning(
+      self.tributary_txn,
+      self.set,
+      latest_substrate_block_to_cosign,
+      intent.block_number,
+    );
+    // Send the message for the processor to start signing
+    TributaryDb::send_message(
+      self.tributary_txn,
+      self.set,
+      messages::coordinator::CoordinatorMessage::CosignSubstrateBlock {
+        session: self.set.session,
+        intent,
+      },
+    );
+  }
+  fn handle_application_tx(&mut self, block_number: u64, tx: Transaction) {
+    let signer = |signed: Signed| SeraiAddress(signed.signer().to_bytes());
+
+    if let TransactionKind::Signed(_, TributarySigned { signer, .. }) = tx.kind() {
+      // Don't handle transactions from those fatally slashed
+      // TODO: The fact they can publish these TXs makes this a notable spam vector
+      if TributaryDb::is_fatally_slashed(
+        self.tributary_txn,
+        self.set,
+        SeraiAddress(signer.to_bytes()),
+      ) {
+        return;
       }
     }
 
-  /// Get a Future which will resolve once the next block has been added.
-  pub async fn next_block_notification(
-    &self,
-  ) -> impl Send + Sync + core::future::Future<Output = Result<(), impl Send + Sync>> {
-    let (tx, rx) = tokio::sync::oneshot::channel();
-    self.network.blockchain.write().await.next_block_notifications.push_back(tx);
-    rx
+    match tx {
+      // Accumulate this vote and fatally slash the participant if past the threshold
+      Transaction::RemoveParticipant { participant, signed } => {
+        let signer = signer(signed);
+
+        // Check the participant voted to be removed actually exists
+        if !self.validators.iter().any(|validator| *validator == participant) {
+          TributaryDb::fatal_slash(
+            self.tributary_txn,
+            self.set,
+            signer,
+            "voted to remove non-existent participant",
+          );
+          return;
+        }
+
+        match TributaryDb::accumulate(
+          self.tributary_txn,
+          self.set,
+          self.validators,
+          self.total_weight,
+          block_number,
+          Topic::RemoveParticipant { participant },
+          signer,
+          self.validator_weights[&signer],
+          &(),
+        ) {
+          DataSet::None => {}
+          DataSet::Participating(_) => {
+            TributaryDb::fatal_slash(self.tributary_txn, self.set, participant, "voted to remove");
+          }
+        };
+      }
+
+      // Send the participation to the processor
+      Transaction::DkgParticipation { participation, signed } => {
+        TributaryDb::send_message(
+          self.tributary_txn,
+          self.set,
+          messages::key_gen::CoordinatorMessage::Participation {
+            session: self.set.session,
+            participant: todo!("TODO"),
+            participation,
+          },
+        );
+      }
+      Transaction::DkgConfirmationPreprocess { attempt, preprocess, signed } => {
+        // Accumulate the preprocesses into our own FROST attempt manager
+        todo!("TODO")
+      }
+      Transaction::DkgConfirmationShare { attempt, share, signed } => {
+        // Accumulate the shares into our own FROST attempt manager
+        todo!("TODO: SetKeysTask")
+      }
+
+      Transaction::Cosign { substrate_block_hash } => {
+        // Update the latest intended-to-be-cosigned Substrate block
+        TributaryDb::set_latest_substrate_block_to_cosign(
+          self.tributary_txn,
+          self.set,
+          substrate_block_hash,
+        );
+        // Start a new cosign if we aren't already working on one
+        self.potentially_start_cosign();
+      }
+      Transaction::Cosigned { substrate_block_hash } => {
+        /*
+          We provide one Cosigned per Cosign transaction, but they have independent orders. This
+          means we may receive Cosigned before Cosign. In order to ensure we only start work on
+          not-yet-Cosigned cosigns, we flag all cosigned blocks as cosigned. Then, when we choose
+          the next block to work on, we won't if it's already been cosigned.
+        */
+        TributaryDb::mark_cosigned(self.tributary_txn, self.set, substrate_block_hash);
+
+        // If we aren't actively cosigning this block, return
+        // This occurs when we have Cosign TXs A, B, C, we received Cosigned for A and start on C,
+        // and then receive Cosigned for B
+        if TributaryDb::actively_cosigning(self.tributary_txn, self.set) !=
+          Some(substrate_block_hash)
+        {
+          return;
+        }
+
+        // Since this is the block we were cosigning, mark us as having finished cosigning
+        TributaryDb::finish_cosigning(self.tributary_txn, self.set);
+
+        // Start working on the next cosign
+        self.potentially_start_cosign();
+      }
+      Transaction::SubstrateBlock { hash } => {
+        // Whitelist all of the IDs this Substrate block causes to be signed
+        let plans = SubstrateBlockPlans::take(self.tributary_txn, self.set, hash).expect(
+          "Transaction::SubstrateBlock locally provided but SubstrateBlockPlans wasn't populated",
+        );
+        for plan in plans {
+          TributaryDb::recognize_topic(
+            self.tributary_txn,
+            self.set,
+            Topic::Sign {
+              id: VariantSignId::Transaction(plan),
+              attempt: 0,
+              round: SigningProtocolRound::Preprocess,
+            },
+          );
+        }
+      }
+      Transaction::Batch { hash } => {
+        // Whitelist the signing of this batch
+        TributaryDb::recognize_topic(
+          self.tributary_txn,
+          self.set,
+          Topic::Sign {
+            id: VariantSignId::Batch(hash),
+            attempt: 0,
+            round: SigningProtocolRound::Preprocess,
+          },
+        );
+      }
+
+      Transaction::SlashReport { slash_points, signed } => {
+        let signer = signer(signed);
+
+        if slash_points.len() != self.validators.len() {
+          TributaryDb::fatal_slash(
+            self.tributary_txn,
+            self.set,
+            signer,
+            "slash report was for a distinct amount of signers",
+          );
+          return;
+        }
+
+        // Accumulate, and if past the threshold, calculate *the* slash report and start signing it
+        match TributaryDb::accumulate(
+          self.tributary_txn,
+          self.set,
+          self.validators,
+          self.total_weight,
+          block_number,
+          Topic::SlashReport,
+          signer,
+          self.validator_weights[&signer],
+          &slash_points,
+        ) {
+          DataSet::None => {}
+          DataSet::Participating(data_set) => {
+            // Find the median reported slashes for this validator
+            /*
+              TODO: This lets 34% perform a fatal slash. That shouldn't be allowed. We need
+              to accept slash reports for a period past the threshold, and only fatally slash if we
+              have a supermajority agree the slash should be fatal. If there isn't a supermajority,
+              but the median believe the slash should be fatal, we need to fallback to a large
+              constant.
+
+              Also, TODO, each slash point should probably be considered as
+              `MAX_KEY_SHARES_PER_SET * BLOCK_TIME` seconds of downtime. As this time crosses
+              various thresholds (1 day, 3 days, etc), a multiplier should be attached.
+            */
+            let mut median_slash_report = Vec::with_capacity(self.validators.len());
+            for i in 0 .. self.validators.len() {
+              let mut this_validator =
+                data_set.values().map(|report| report[i]).collect::<Vec<_>>();
+              this_validator.sort_unstable();
+              // Choose the median, where if there are two median values, the lower one is chosen
+              let median_index = if (this_validator.len() % 2) == 1 {
+                this_validator.len() / 2
+              } else {
+                (this_validator.len() / 2) - 1
+              };
+              median_slash_report.push(this_validator[median_index]);
+            }
+
+            // We only publish slashes for the `f` worst performers to:
+            // 1) Effect amnesty if there were network disruptions which affected everyone
+            // 2) Ensure the signing threshold doesn't have a disincentive to do their job
+
+            // Find the worst performer within the signing threshold's slash points
+            let f = (self.validators.len() - 1) / 3;
+            let worst_validator_in_supermajority_slash_points = {
+              let mut sorted_slash_points = median_slash_report.clone();
+              sorted_slash_points.sort_unstable();
+              // This won't be a valid index if `f == 0`, which means we don't have any validators
+              // to slash
+              let index_of_first_validator_to_slash = self.validators.len() - f;
+              let index_of_worst_validator_in_supermajority = index_of_first_validator_to_slash - 1;
+              sorted_slash_points[index_of_worst_validator_in_supermajority]
+            };
+
+            // Perform the amortization
+            for slash_points in &mut median_slash_report {
+              *slash_points =
+                slash_points.saturating_sub(worst_validator_in_supermajority_slash_points)
+            }
+            let amortized_slash_report = median_slash_report;
+
+            // Create the resulting slash report
+            let mut slash_report = vec![];
+            for (validator, points) in self.validators.iter().copied().zip(amortized_slash_report) {
+              // TODO: Natively store this as a `Slash`
+              if points == u32::MAX {
+                slash_report.push(Slash::Fatal);
+              } else {
+                slash_report.push(Slash::Points(points));
+              }
+            }
+            assert!(slash_report.len() <= f);
+
+            // Recognize the topic for signing the slash report
+            TributaryDb::recognize_topic(
+              self.tributary_txn,
+              self.set,
+              Topic::Sign {
+                id: VariantSignId::SlashReport,
+                attempt: 0,
+                round: SigningProtocolRound::Preprocess,
+              },
+            );
+            // Send the message for the processor to start signing
+            TributaryDb::send_message(
+              self.tributary_txn,
+              self.set,
+              messages::coordinator::CoordinatorMessage::SignSlashReport {
+                session: self.set.session,
+                report: slash_report,
+              },
+            );
+          }
+        };
+      }
+
+      Transaction::Sign { id, attempt, round, data, signed } => {
+        let topic = Topic::Sign { id, attempt, round };
+        let signer = signer(signed);
+
+        if u64::try_from(data.len()).unwrap() != self.validator_weights[&signer] {
+          TributaryDb::fatal_slash(
+            self.tributary_txn,
+            self.set,
+            signer,
+            "signer signed with a distinct amount of key shares than they had key shares",
+          );
+          return;
+        }
+
+        match TributaryDb::accumulate(
+          self.tributary_txn,
+          self.set,
+          self.validators,
+          self.total_weight,
+          block_number,
+          topic,
+          signer,
+          self.validator_weights[&signer],
+          &data,
+        ) {
+          DataSet::None => {}
+          DataSet::Participating(data_set) => {
+            let id = topic.sign_id(self.set).expect("Topic::Sign didn't have SignId");
+            let flatten_data_set = |data_set| todo!("TODO");
+            let data_set = flatten_data_set(data_set);
+            TributaryDb::send_message(
+              self.tributary_txn,
+              self.set,
+              match round {
+                SigningProtocolRound::Preprocess => {
+                  messages::sign::CoordinatorMessage::Preprocesses { id, preprocesses: data_set }
+                }
+                SigningProtocolRound::Share => {
+                  messages::sign::CoordinatorMessage::Shares { id, shares: data_set }
+                }
+              },
+            )
+          }
+        };
+      }
     }
   }
 
-#[derive(Clone)]
-pub struct TributaryReader<D: Db, T: TransactionTrait>(D, [u8; 32], PhantomData<T>);
-impl<D: Db, T: TransactionTrait> TributaryReader<D, T> {
-  pub fn genesis(&self) -> [u8; 32] {
-    self.1
+  fn handle_block(mut self, block_number: u64, block: Block<Transaction>) {
+    TributaryDb::start_of_block(self.tributary_txn, self.set, block_number);
+
+    for tx in block.transactions {
+      match tx {
+        TributaryTransaction::Tendermint(TendermintTx::SlashEvidence(ev)) => {
+          // Since the evidence is on the chain, it will have already been validated
+          // We can just punish the signer
+          let data = match ev {
+            Evidence::ConflictingMessages(first, second) => (first, Some(second)),
+            Evidence::InvalidPrecommit(first) | Evidence::InvalidValidRound(first) => (first, None),
+          };
+          let msgs = (
+            decode_signed_message::<TendermintNetwork<TD, Transaction, P>>(&data.0).unwrap(),
+            if data.1.is_some() {
+              Some(
+                decode_signed_message::<TendermintNetwork<TD, Transaction, P>>(&data.1.unwrap())
+                  .unwrap(),
+              )
+            } else {
+              None
+            },
+          );
+
+          // Since anything with evidence is fundamentally faulty behavior, not just temporal
+          // errors, mark the node as fatally slashed
+          TributaryDb::fatal_slash(
+            self.tributary_txn,
+            self.set,
+            SeraiAddress(msgs.0.msg.sender),
+            &format!("invalid tendermint messages: {msgs:?}"),
+          );
+        }
+        TributaryTransaction::Application(tx) => {
+          self.handle_application_tx(block_number, tx);
+        }
+      }
+    }
+  }
 }
 
-  // Since these values are static once set, they can be safely read from the database without lock
-  // acquisition
-  pub fn block(&self, hash: &[u8; 32]) -> Option<Block<T>> {
-    Blockchain::<D, T>::block_from_db(&self.0, self.1, hash)
-  }
-  pub fn commit(&self, hash: &[u8; 32]) -> Option<Vec<u8>> {
-    Blockchain::<D, T>::commit_from_db(&self.0, self.1, hash)
-  }
-  pub fn parsed_commit(&self, hash: &[u8; 32]) -> Option<Commit<Validators>> {
-    self.commit(hash).map(|commit| Commit::<Validators>::decode(&mut commit.as_ref()).unwrap())
-  }
-  pub fn block_after(&self, hash: &[u8; 32]) -> Option<[u8; 32]> {
-    Blockchain::<D, T>::block_after(&self.0, self.1, hash)
-  }
-  pub fn time_of_block(&self, hash: &[u8; 32]) -> Option<u64> {
-    self
-      .commit(hash)
-      .map(|commit| Commit::<Validators>::decode(&mut commit.as_ref()).unwrap().end_time)
+/// The task to scan the Tributary, populating `ProcessorMessages`.
+pub struct ScanTributaryTask<TD: Db, P: P2p> {
+  tributary_db: TD,
+  set: ValidatorSet,
+  validators: Vec<SeraiAddress>,
+  total_weight: u64,
+  validator_weights: HashMap<SeraiAddress, u64>,
+  tributary: TributaryReader<TD, Transaction>,
+  _p2p: PhantomData<P>,
 }
 
-  pub fn locally_provided_txs_in_block(&self, hash: &[u8; 32], order: &str) -> bool {
-    Blockchain::<D, T>::locally_provided_txs_in_block(&self.0, &self.1, hash, order)
+impl<TD: Db, P: P2p> ScanTributaryTask<TD, P> {
+  /// Create a new instance of this task.
+  pub fn new(
+    tributary_db: TD,
+    new_set: &NewSetInformation,
+    tributary: TributaryReader<TD, Transaction>,
+  ) -> Self {
+    let mut validators = Vec::with_capacity(new_set.validators.len());
+    let mut total_weight = 0;
+    let mut validator_weights = HashMap::with_capacity(new_set.validators.len());
+    for (validator, weight) in new_set.validators.iter().copied() {
+      let validator = SeraiAddress::from(validator);
+      let weight = u64::from(weight);
+      validators.push(validator);
+      total_weight += weight;
+      validator_weights.insert(validator, weight);
     }
 
-  // This isn't static, yet can be read with only minor discrepancy risks
-  pub fn tip(&self) -> [u8; 32] {
-    Blockchain::<D, T>::tip_from_db(&self.0, self.1)
+    ScanTributaryTask {
+      tributary_db,
+      set: new_set.set,
+      validators,
+      total_weight,
+      validator_weights,
+      tributary,
+      _p2p: PhantomData,
     }
   }
+}
+
+impl<TD: Db, P: P2p> ContinuallyRan for ScanTributaryTask<TD, P> {
+  type Error = String;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
+    async move {
+      let (mut last_block_number, mut last_block_hash) =
+        TributaryDb::last_handled_tributary_block(&self.tributary_db, self.set)
+          .unwrap_or((0, self.tributary.genesis()));
+
+      let mut made_progress = false;
+      while let Some(next) = self.tributary.block_after(&last_block_hash) {
+        let block = self.tributary.block(&next).unwrap();
+        let block_number = last_block_number + 1;
+        let block_hash = block.hash();
+
+        // Make sure we have all of the provided transactions for this block
+        for tx in &block.transactions {
+          let TransactionKind::Provided(order) = tx.kind() else {
+            continue;
+          };
+
+          // make sure we have all the provided txs in this block locally
+          if !self.tributary.locally_provided_txs_in_block(&block_hash, order) {
+            return Err(format!(
+              "didn't have the provided Transactions on-chain for set (ephemeral error): {:?}",
+              self.set
+            ));
+          }
+        }
+
+        let mut tributary_txn = self.tributary_db.txn();
+        (ScanBlock {
+          _td: PhantomData::<TD>,
+          _p2p: PhantomData::<P>,
+          tributary_txn: &mut tributary_txn,
+          set: self.set,
+          validators: &self.validators,
+          total_weight: self.total_weight,
+          validator_weights: &self.validator_weights,
+        })
+        .handle_block(block_number, block);
+        TributaryDb::set_last_handled_tributary_block(
+          &mut tributary_txn,
+          self.set,
+          block_number,
+          block_hash,
+        );
+        last_block_number = block_number;
+        last_block_hash = block_hash;
+        tributary_txn.commit();
+
+        made_progress = true;
+      }
+
+      Ok(made_progress)
+    }
+  }
+}
+
+/// Create the Transaction::SlashReport to publish per the local view.
+pub fn slash_report_transaction(getter: &impl Get, set: &NewSetInformation) -> Transaction {
+  let mut slash_points = Vec::with_capacity(set.validators.len());
+  for (validator, _weight) in set.validators.iter().copied() {
+    let validator = SeraiAddress::from(validator);
+    slash_points.push(SlashPoints::get(getter, set.set, validator).unwrap_or(0));
+  }
+  Transaction::SlashReport { slash_points, signed: Signed::default() }
+}

coordinator/tributary/src/transaction.rs

@@ -1,218 +1,365 @@
-use core::fmt::Debug;
+use core::{ops::Deref, fmt::Debug};
 use std::io;
 
-use zeroize::Zeroize;
-use thiserror::Error;
-
-use blake2::{Digest, Blake2b512};
+use zeroize::Zeroizing;
+use rand_core::{RngCore, CryptoRng};
 
+use blake2::{digest::typenum::U32, Digest, Blake2b};
 use ciphersuite::{
-  group::{Group, GroupEncoding},
+  group::{ff::Field, Group, GroupEncoding},
   Ciphersuite, Ristretto,
 };
 use schnorr::SchnorrSignature;
 
-use crate::{TRANSACTION_SIZE_LIMIT, ReadWrite};
+use scale::Encode;
+use borsh::{BorshSerialize, BorshDeserialize};
 
-#[derive(Clone, PartialEq, Eq, Debug, Error)]
-pub enum TransactionError {
-  /// Transaction exceeded the size limit.
-  #[error("transaction is too large")]
-  TooLargeTransaction,
-  /// Transaction's signer isn't a participant.
-  #[error("invalid signer")]
-  InvalidSigner,
-  /// Transaction's nonce isn't the prior nonce plus one.
-  #[error("invalid nonce")]
-  InvalidNonce,
-  /// Transaction's signature is invalid.
-  #[error("invalid signature")]
-  InvalidSignature,
-  /// Transaction's content is invalid.
-  #[error("transaction content is invalid")]
-  InvalidContent,
-  /// Transaction's signer has too many transactions in the mempool.
-  #[error("signer has too many transactions in the mempool")]
-  TooManyInMempool,
-  /// Provided Transaction added to mempool.
-  #[error("provided transaction added to mempool")]
-  ProvidedAddedToMempool,
+use serai_client::{primitives::SeraiAddress, validator_sets::primitives::MAX_KEY_SHARES_PER_SET};
+
+use messages::sign::VariantSignId;
+
+use tributary_sdk::{
+  ReadWrite,
+  transaction::{
+    Signed as TributarySigned, TransactionError, TransactionKind, Transaction as TransactionTrait,
+  },
+};
+
+/// The round this data is for, within a signing protocol.
+#[derive(Clone, Copy, PartialEq, Eq, Debug, Encode, BorshSerialize, BorshDeserialize)]
+pub enum SigningProtocolRound {
+  /// A preprocess.
+  Preprocess,
+  /// A signature share.
+  Share,
 }
 
-/// Data for a signed transaction.
-#[derive(Clone, PartialEq, Eq, Debug)]
+impl SigningProtocolRound {
+  fn nonce(&self) -> u32 {
+    match self {
+      SigningProtocolRound::Preprocess => 0,
+      SigningProtocolRound::Share => 1,
+    }
+  }
+}
+
+/// `tributary::Signed` but without the nonce.
+///
+/// All of our nonces are deterministic to the type of transaction and fields within.
+#[derive(Clone, Copy, PartialEq, Eq, Debug)]
 pub struct Signed {
-  pub signer: <Ristretto as Ciphersuite>::G,
-  pub nonce: u32,
-  pub signature: SchnorrSignature<Ristretto>,
+  /// The signer.
+  signer: <Ristretto as Ciphersuite>::G,
+  /// The signature.
+  signature: SchnorrSignature<Ristretto>,
 }
 
-impl ReadWrite for Signed {
-  fn read<R: io::Read>(reader: &mut R) -> io::Result<Self> {
-    let signer = Ristretto::read_G(reader)?;
-
-    let mut nonce = [0; 4];
-    reader.read_exact(&mut nonce)?;
-    let nonce = u32::from_le_bytes(nonce);
-    if nonce >= (u32::MAX - 1) {
-      Err(io::Error::other("nonce exceeded limit"))?;
-    }
-
-    let mut signature = SchnorrSignature::<Ristretto>::read(reader)?;
-    if signature.R.is_identity().into() {
-      // Anyone malicious could remove this and try to find zero signatures
-      // We should never produce zero signatures though meaning this should never come up
-      // If it does somehow come up, this is a decent courtesy
-      signature.zeroize();
-      Err(io::Error::other("signature nonce was identity"))?;
-    }
-
-    Ok(Signed { signer, nonce, signature })
-  }
-
-  fn write<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
-    // This is either an invalid signature or a private key leak
-    if self.signature.R.is_identity().into() {
-      Err(io::Error::other("signature nonce was identity"))?;
-    }
-    writer.write_all(&self.signer.to_bytes())?;
-    writer.write_all(&self.nonce.to_le_bytes())?;
+impl BorshSerialize for Signed {
+  fn serialize<W: io::Write>(&self, writer: &mut W) -> Result<(), io::Error> {
+    writer.write_all(self.signer.to_bytes().as_ref())?;
     self.signature.write(writer)
   }
 }
+impl BorshDeserialize for Signed {
+  fn deserialize_reader<R: io::Read>(reader: &mut R) -> Result<Self, io::Error> {
+    let signer = Ristretto::read_G(reader)?;
+    let signature = SchnorrSignature::read(reader)?;
+    Ok(Self { signer, signature })
+  }
+}
 
 impl Signed {
-  pub fn read_without_nonce<R: io::Read>(reader: &mut R, nonce: u32) -> io::Result<Self> {
-    let signer = Ristretto::read_G(reader)?;
-
-    let mut signature = SchnorrSignature::<Ristretto>::read(reader)?;
-    if signature.R.is_identity().into() {
-      // Anyone malicious could remove this and try to find zero signatures
-      // We should never produce zero signatures though meaning this should never come up
-      // If it does somehow come up, this is a decent courtesy
-      signature.zeroize();
-      Err(io::Error::other("signature nonce was identity"))?;
+  /// Fetch the signer.
+  pub(crate) fn signer(&self) -> <Ristretto as Ciphersuite>::G {
+    self.signer
   }
 
-    Ok(Signed { signer, nonce, signature })
-  }
-
-  pub fn write_without_nonce<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
-    // This is either an invalid signature or a private key leak
-    if self.signature.R.is_identity().into() {
-      Err(io::Error::other("signature nonce was identity"))?;
-    }
-    writer.write_all(&self.signer.to_bytes())?;
-    self.signature.write(writer)
+  /// Provide a nonce to convert a `Signed` into a `tributary::Signed`.
+  fn to_tributary_signed(self, nonce: u32) -> TributarySigned {
+    TributarySigned { signer: self.signer, nonce, signature: self.signature }
   }
 }
 
-#[allow(clippy::large_enum_variant)]
-#[derive(Clone, PartialEq, Eq, Debug)]
-pub enum TransactionKind {
-  /// This transaction should be provided by every validator, in an exact order.
+impl Default for Signed {
+  fn default() -> Self {
+    Self {
+      signer: <Ristretto as Ciphersuite>::G::identity(),
+      signature: SchnorrSignature {
+        R: <Ristretto as Ciphersuite>::G::identity(),
+        s: <Ristretto as Ciphersuite>::F::ZERO,
+      },
+    }
+  }
+}
+
+/// The Tributary transaction definition used by Serai
+#[derive(Clone, PartialEq, Eq, Debug, BorshSerialize, BorshDeserialize)]
+pub enum Transaction {
+  /// A vote to remove a participant for invalid behavior
+  RemoveParticipant {
+    /// The participant to remove
+    participant: SeraiAddress,
+    /// The transaction's signer and signature
+    signed: Signed,
+  },
+
+  /// A participation in the DKG
+  DkgParticipation {
+    /// The serialized participation
+    participation: Vec<u8>,
+    /// The transaction's signer and signature
+    signed: Signed,
+  },
+  /// The preprocess to confirm the DKG results on-chain
+  DkgConfirmationPreprocess {
+    /// The attempt number of this signing protocol
+    attempt: u32,
+    /// The preprocess
+    preprocess: [u8; 64],
+    /// The transaction's signer and signature
+    signed: Signed,
+  },
+  /// The signature share to confirm the DKG results on-chain
+  DkgConfirmationShare {
+    /// The attempt number of this signing protocol
+    attempt: u32,
+    /// The signature share
+    share: [u8; 32],
+    /// The transaction's signer and signature
+    signed: Signed,
+  },
+
+  /// Intend to cosign a finalized Substrate block
   ///
-  /// The contained static string names the orderer to use. This allows two distinct provided
-  /// transaction kinds, without a synchronized order, to be ordered within their own kind without
-  /// requiring ordering with each other.
+  /// When the time comes to start a new cosigning protocol, the most recent Substrate block will
+  /// be the one selected to be cosigned.
+  Cosign {
+    /// The hash of the Substrate block to cosign
+    substrate_block_hash: [u8; 32],
+  },
+
+  /// Note an intended-to-be-cosigned Substrate block as cosigned
   ///
-  /// The only malleability is in when this transaction appears on chain. The block producer will
-  /// include it when they have it. Block verification will fail for validators without it.
+  /// After producing this cosign, we need to start work on the latest intended-to-be cosigned
+  /// block. That requires agreement on when this cosign was produced, which we solve by noting
+  /// this cosign on-chain.
   ///
-  /// If a supermajority of validators produce a commit for a block with a provided transaction
-  /// which isn't locally held, the block will be added to the local chain. When the transaction is
-  /// locally provided, it will be compared for correctness to the on-chain version
+  /// We ideally don't have this transaction at all. The coordinator, without access to any of the
+  /// key shares, could observe the FROST signing session and determine a successful completion.
+  /// Unfortunately, that functionality is not present in modular-frost, so we do need to support
+  /// *some* asynchronous flow (where the processor or P2P network informs us of the successful
+  /// completion).
   ///
-  /// In order to ensure TXs aren't accidentally provided multiple times, all provided transactions
-  /// must have a unique hash which is also unique to all Unsigned transactions.
-  Provided(&'static str),
-
-  /// An unsigned transaction, only able to be included by the block producer.
+  /// If we use a `Provided` transaction, that requires everyone observe this cosign.
   ///
-  /// Once an Unsigned transaction is included on-chain, it may not be included again. In order to
-  /// have multiple Unsigned transactions with the same values included on-chain, some distinct
-  /// nonce must be included in order to cause a distinct hash.
+  /// If we use an `Unsigned` transaction, we can't verify the cosign signature inside
+  /// `Transaction::verify` unless we embedded the full `SignedCosign` on-chain. The issue is since
+  /// a Tributary is stateless with regards to the on-chain logic, including `Transaction::verify`,
+  /// we can't verify the signature against the group's public key unless we also include that (but
+  /// then we open a DoS where arbitrary group keys are specified to cause inclusion of arbitrary
+  /// blobs on chain).
   ///
-  /// The hash must also be unique with all Provided transactions.
-  Unsigned,
-
-  /// A signed transaction.
-  Signed(Vec<u8>, Signed),
-}
-
-// TODO: Should this be renamed TransactionTrait now that a literal Transaction exists?
-// Or should the literal Transaction be renamed to Event?
-pub trait Transaction: 'static + Send + Sync + Clone + Eq + Debug + ReadWrite {
-  /// Return what type of transaction this is.
-  fn kind(&self) -> TransactionKind;
-
-  /// Return the hash of this transaction.
+  /// If we use a `Signed` transaction, we mitigate the DoS risk by having someone to fatally
+  /// slash. We have horrible performance though as for 100 validators, all 100 will publish this
+  /// transaction.
   ///
-  /// The hash must NOT commit to the signature.
-  fn hash(&self) -> [u8; 32];
-
-  /// Perform transaction-specific verification.
-  fn verify(&self) -> Result<(), TransactionError>;
-
-  /// Obtain the challenge for this transaction's signature.
+  /// We could use a signed `Unsigned` transaction, where it includes a signer and signature but
+  /// isn't technically a Signed transaction. This lets us de-duplicate the transaction premised on
+  /// its contents.
   ///
-  /// Do not override this unless you know what you're doing.
+  /// The optimal choice is likely to use a `Provided` transaction. We don't actually need to
+  /// observe the produced cosign (which is ephemeral). As long as it's agreed the cosign in
+  /// question no longer needs to produced, which would mean the cosigning protocol at-large
+  /// cosigning the block in question, it'd be safe to provide this and move on to the next cosign.
+  Cosigned {
+    /// The hash of the Substrate block which was cosigned
+    substrate_block_hash: [u8; 32],
+  },
+
+  /// Acknowledge a Substrate block
   ///
-  /// Panics if called on non-signed transactions.
-  fn sig_hash(&self, genesis: [u8; 32]) -> <Ristretto as Ciphersuite>::F {
-    match self.kind() {
-      TransactionKind::Signed(order, Signed { signature, .. }) => {
-        <Ristretto as Ciphersuite>::F::from_bytes_mod_order_wide(
-          &Blake2b512::digest(
-            [
-              b"Tributary Signed Transaction",
-              genesis.as_ref(),
-              &self.hash(),
-              order.as_ref(),
-              signature.R.to_bytes().as_ref(),
-            ]
-            .concat(),
-          )
-          .into(),
-        )
+  /// This is provided after the block has been cosigned.
+  ///
+  /// With the acknowledgement of a Substrate block, we can whitelist all the `VariantSignId`s
+  /// resulting from its handling.
+  SubstrateBlock {
+    /// The hash of the Substrate block
+    hash: [u8; 32],
+  },
+
+  /// Acknowledge a Batch
+  ///
+  /// Once everyone has acknowledged the Batch, we can begin signing it.
+  Batch {
+    /// The hash of the Batch's serialization.
+    ///
+    /// Generally, we refer to a Batch by its ID/the hash of its instructions. Here, we want to
+    /// ensure consensus on the Batch, and achieving consensus on its hash is the most effective
+    /// way to do that.
+    hash: [u8; 32],
+  },
+
+  /// Data from a signing protocol.
+  Sign {
+    /// The ID of the object being signed
+    id: VariantSignId,
+    /// The attempt number of this signing protocol
+    attempt: u32,
+    /// The round this data is for, within the signing protocol
+    round: SigningProtocolRound,
+    /// The data itself
+    ///
+    /// There will be `n` blobs of data where `n` is the amount of key shares the validator sending
+    /// this transaction has.
+    data: Vec<Vec<u8>>,
+    /// The transaction's signer and signature
+    signed: Signed,
+  },
+
+  /// The local view of slashes observed by the transaction's sender
+  SlashReport {
+    /// The slash points accrued by each validator
+    slash_points: Vec<u32>,
+    /// The transaction's signer and signature
+    signed: Signed,
+  },
 }
-      _ => panic!("sig_hash called on non-signed transaction"),
+
+impl ReadWrite for Transaction {
+  fn read<R: io::Read>(reader: &mut R) -> io::Result<Self> {
+    borsh::from_reader(reader)
+  }
+
+  fn write<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
+    borsh::to_writer(writer, self)
+  }
+}
+
+impl TransactionTrait for Transaction {
+  fn kind(&self) -> TransactionKind {
+    match self {
+      Transaction::RemoveParticipant { participant, signed } => TransactionKind::Signed(
+        (b"RemoveParticipant", participant).encode(),
+        signed.to_tributary_signed(0),
+      ),
+
+      Transaction::DkgParticipation { signed, .. } => {
+        TransactionKind::Signed(b"DkgParticipation".encode(), signed.to_tributary_signed(0))
+      }
+      Transaction::DkgConfirmationPreprocess { attempt, signed, .. } => TransactionKind::Signed(
+        (b"DkgConfirmation", attempt).encode(),
+        signed.to_tributary_signed(0),
+      ),
+      Transaction::DkgConfirmationShare { attempt, signed, .. } => TransactionKind::Signed(
+        (b"DkgConfirmation", attempt).encode(),
+        signed.to_tributary_signed(1),
+      ),
+
+      Transaction::Cosign { .. } => TransactionKind::Provided("Cosign"),
+      Transaction::Cosigned { .. } => TransactionKind::Provided("Cosigned"),
+      // TODO: Provide this
+      Transaction::SubstrateBlock { .. } => TransactionKind::Provided("SubstrateBlock"),
+      // TODO: Provide this
+      Transaction::Batch { .. } => TransactionKind::Provided("Batch"),
+
+      Transaction::Sign { id, attempt, round, signed, .. } => TransactionKind::Signed(
+        (b"Sign", id, attempt).encode(),
+        signed.to_tributary_signed(round.nonce()),
+      ),
+
+      Transaction::SlashReport { signed, .. } => {
+        TransactionKind::Signed(b"SlashReport".encode(), signed.to_tributary_signed(0))
       }
     }
   }
 
-pub trait GAIN: FnMut(&<Ristretto as Ciphersuite>::G, &[u8]) -> Option<u32> {}
-impl<F: FnMut(&<Ristretto as Ciphersuite>::G, &[u8]) -> Option<u32>> GAIN for F {}
-
-pub(crate) fn verify_transaction<F: GAIN, T: Transaction>(
-  tx: &T,
-  genesis: [u8; 32],
-  get_and_increment_nonce: &mut F,
-) -> Result<(), TransactionError> {
-  if tx.serialize().len() > TRANSACTION_SIZE_LIMIT {
-    Err(TransactionError::TooLargeTransaction)?;
+  fn hash(&self) -> [u8; 32] {
+    let mut tx = ReadWrite::serialize(self);
+    if let TransactionKind::Signed(_, signed) = self.kind() {
+      // Make sure the part we're cutting off is the signature
+      assert_eq!(tx.drain((tx.len() - 64) ..).collect::<Vec<_>>(), signed.signature.serialize());
+    }
+    Blake2b::<U32>::digest(&tx).into()
   }
 
-  tx.verify()?;
+  // This is a stateless verification which we use to enforce some size limits.
+  fn verify(&self) -> Result<(), TransactionError> {
+    #[allow(clippy::match_same_arms)]
+    match self {
+      // Fixed-length TX
+      Transaction::RemoveParticipant { .. } => {}
 
-  match tx.kind() {
-    TransactionKind::Provided(_) | TransactionKind::Unsigned => {}
-    TransactionKind::Signed(order, Signed { signer, nonce, signature }) => {
-      if let Some(next_nonce) = get_and_increment_nonce(&signer, &order) {
-        if nonce != next_nonce {
-          Err(TransactionError::InvalidNonce)?;
+      // TODO: MAX_DKG_PARTICIPATION_LEN
+      Transaction::DkgParticipation { .. } => {}
+      // These are fixed-length TXs
+      Transaction::DkgConfirmationPreprocess { .. } | Transaction::DkgConfirmationShare { .. } => {}
+
+      // Provided TXs
+      Transaction::Cosign { .. } |
+      Transaction::Cosigned { .. } |
+      Transaction::SubstrateBlock { .. } |
+      Transaction::Batch { .. } => {}
+
+      Transaction::Sign { data, .. } => {
+        if data.len() > usize::from(MAX_KEY_SHARES_PER_SET) {
+          Err(TransactionError::InvalidContent)?
         }
-      } else {
-        // Not a participant
-        Err(TransactionError::InvalidSigner)?;
+        // TODO: MAX_SIGN_LEN
       }
 
-      // TODO: Use a batch verification here
-      if !signature.verify(signer, tx.sig_hash(genesis)) {
-        Err(TransactionError::InvalidSignature)?;
+      Transaction::SlashReport { slash_points, .. } => {
+        if slash_points.len() > usize::from(MAX_KEY_SHARES_PER_SET) {
+          Err(TransactionError::InvalidContent)?
         }
       }
-  }
-
+    };
     Ok(())
   }
+}
+
+impl Transaction {
+  /// Sign a transaction.
+  ///
+  /// Panics if signing a transaction whose type isn't `TransactionKind::Signed`.
+  pub fn sign<R: RngCore + CryptoRng>(
+    &mut self,
+    rng: &mut R,
+    genesis: [u8; 32],
+    key: &Zeroizing<<Ristretto as Ciphersuite>::F>,
+  ) {
+    fn signed(tx: &mut Transaction) -> &mut Signed {
+      #[allow(clippy::match_same_arms)] // This doesn't make semantic sense here
+      match tx {
+        Transaction::RemoveParticipant { ref mut signed, .. } |
+        Transaction::DkgParticipation { ref mut signed, .. } |
+        Transaction::DkgConfirmationPreprocess { ref mut signed, .. } => signed,
+        Transaction::DkgConfirmationShare { ref mut signed, .. } => signed,
+
+        Transaction::Cosign { .. } => panic!("signing CosignSubstrateBlock"),
+        Transaction::Cosigned { .. } => panic!("signing Cosigned"),
+        Transaction::SubstrateBlock { .. } => panic!("signing SubstrateBlock"),
+        Transaction::Batch { .. } => panic!("signing Batch"),
+
+        Transaction::Sign { ref mut signed, .. } => signed,
+
+        Transaction::SlashReport { ref mut signed, .. } => signed,
+      }
+    }
+
+    // Decide the nonce to sign with
+    let sig_nonce = Zeroizing::new(<Ristretto as Ciphersuite>::F::random(rng));
+
+    {
+      // Set the signer and the nonce
+      let signed = signed(self);
+      signed.signer = Ristretto::generator() * key.deref();
+      signed.signature.R = <Ristretto as Ciphersuite>::generator() * sig_nonce.deref();
+    }
+
+    // Get the signature hash (which now includes `R || A` making it valid as the challenge)
+    let sig_hash = self.sig_hash(genesis);
+
+    // Sign the signature
+    signed(self).signature = SchnorrSignature::<Ristretto>::sign(key, sig_nonce, sig_hash);
+  }
+}

deny.toml

@@ -72,9 +72,12 @@ exceptions = [
   { allow = ["AGPL-3.0"], name = "serai-ethereum-processor" },
   { allow = ["AGPL-3.0"], name = "serai-monero-processor" },
 
-  { allow = ["AGPL-3.0"], name = "tributary-chain" },
+  { allow = ["AGPL-3.0"], name = "tributary-sdk" },
   { allow = ["AGPL-3.0"], name = "serai-cosign" },
   { allow = ["AGPL-3.0"], name = "serai-coordinator-substrate" },
+  { allow = ["AGPL-3.0"], name = "serai-coordinator-tributary" },
+  { allow = ["AGPL-3.0"], name = "serai-coordinator-p2p" },
+  { allow = ["AGPL-3.0"], name = "serai-coordinator-libp2p-p2p" },
   { allow = ["AGPL-3.0"], name = "serai-coordinator" },
 
   { allow = ["AGPL-3.0"], name = "serai-coins-pallet" },

message-queue/src/client.rs

@@ -64,22 +64,20 @@ impl MessageQueue {
     Self::new(service, url, priv_key)
   }
 
-  #[must_use]
-  async fn send(socket: &mut TcpStream, msg: MessageQueueRequest) -> bool {
+  async fn send(socket: &mut TcpStream, msg: MessageQueueRequest) -> Result<(), String> {
     let msg = borsh::to_vec(&msg).unwrap();
-    let Ok(()) = socket.write_all(&u32::try_from(msg.len()).unwrap().to_le_bytes()).await else {
-      log::warn!("couldn't send the message len");
-      return false;
+    match socket.write_all(&u32::try_from(msg.len()).unwrap().to_le_bytes()).await {
+      Ok(()) => {}
+      Err(e) => Err(format!("couldn't send the message len: {e:?}"))?,
     };
-    let Ok(()) = socket.write_all(&msg).await else {
-      log::warn!("couldn't write the message");
-      return false;
-    };
-    true
+    match socket.write_all(&msg).await {
+      Ok(()) => {}
+      Err(e) => Err(format!("couldn't write the message: {e:?}"))?,
+    }
+    Ok(())
   }
 
-  pub async fn queue(&self, metadata: Metadata, msg: Vec<u8>) {
-    // TODO: Should this use OsRng? Deterministic or deterministic + random may be better.
+  pub async fn queue(&self, metadata: Metadata, msg: Vec<u8>) -> Result<(), String> {
     let nonce = Zeroizing::new(<Ristretto as Ciphersuite>::F::random(&mut OsRng));
     let nonce_pub = Ristretto::generator() * nonce.deref();
     let sig = SchnorrSignature::<Ristretto>::sign(
@@ -97,6 +95,21 @@ impl MessageQueue {
     .serialize();
 
     let msg = MessageQueueRequest::Queue { meta: metadata, msg, sig };
+
+    let mut socket = match TcpStream::connect(&self.url).await {
+      Ok(socket) => socket,
+      Err(e) => Err(format!("failed to connect to the message-queue service: {e:?}"))?,
+    };
+    Self::send(&mut socket, msg.clone()).await?;
+    match socket.read_u8().await {
+      Ok(1) => {}
+      Ok(b) => Err(format!("message-queue didn't return for 1 for its ack, recieved: {b}"))?,
+      Err(e) => Err(format!("failed to read the response from the message-queue service: {e:?}"))?,
+    }
+    Ok(())
+  }
+
+  pub async fn queue_with_retry(&self, metadata: Metadata, msg: Vec<u8>) {
     let mut first = true;
     loop {
       // Sleep, so we don't hammer re-attempts
@@ -105,16 +118,11 @@ impl MessageQueue {
       }
       first = false;
 
-      let Ok(mut socket) = TcpStream::connect(&self.url).await else { continue };
-      if !Self::send(&mut socket, msg.clone()).await {
-        continue;
-      }
-      if socket.read_u8().await.ok() != Some(1) {
-        continue;
-      }
+      if self.queue(metadata.clone(), msg.clone()).await.is_ok() {
         break;
       }
     }
+  }
 
   pub async fn next(&self, from: Service) -> QueuedMessage {
     let msg = MessageQueueRequest::Next { from, to: self.service };
@@ -136,7 +144,7 @@ impl MessageQueue {
       log::trace!("opened socket for next");
 
       loop {
-        if !Self::send(&mut socket, msg.clone()).await {
+        if Self::send(&mut socket, msg.clone()).await.is_err() {
           continue 'outer;
         }
         let status = match socket.read_u8().await {
@@ -224,7 +232,7 @@ impl MessageQueue {
       first = false;
 
       let Ok(mut socket) = TcpStream::connect(&self.url).await else { continue };
-      if !Self::send(&mut socket, msg.clone()).await {
+      if Self::send(&mut socket, msg.clone()).await.is_err() {
         continue;
       }
       if socket.read_u8().await.ok() != Some(1) {

processor/bin/src/coordinator.rs

@@ -95,6 +95,7 @@ impl Coordinator {
           message_queue.ack(Service::Coordinator, msg.id).await;
 
           // Fire that there's a new message
+          // This assumes the success path, not the just-rebooted-path
           received_message_send
             .send(())
             .expect("failed to tell the Coordinator there's a new message");
@@ -103,6 +104,7 @@ impl Coordinator {
     });
 
     // Spawn a task to send messages to the message-queue
+    // TODO: Define a proper task for this and remove use of queue_with_retry
     tokio::spawn({
       let mut db = db.clone();
       async move {
@@ -115,12 +117,12 @@ impl Coordinator {
                 to: Service::Coordinator,
                 intent: borsh::from_slice::<messages::ProcessorMessage>(&msg).unwrap().intent(),
               };
-              message_queue.queue(metadata, msg).await;
+              message_queue.queue_with_retry(metadata, msg).await;
               txn.commit();
             }
             None => {
               let _ =
-                tokio::time::timeout(core::time::Duration::from_secs(60), sent_message_recv.recv())
+                tokio::time::timeout(core::time::Duration::from_secs(6), sent_message_recv.recv())
                   .await;
             }
           }

processor/bitcoin/src/txindex.rs

@@ -39,7 +39,9 @@ pub(crate) fn script_pubkey_for_on_chain_output(
 pub(crate) struct TxIndexTask<D: Db>(pub(crate) Rpc<D>);
 
 impl<D: Db> ContinuallyRan for TxIndexTask<D> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = String;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       let latest_block_number = self
         .0

processor/messages/Cargo.toml

@@ -29,3 +29,5 @@ serai-primitives = { path = "../../substrate/primitives", default-features = fal
 in-instructions-primitives = { package = "serai-in-instructions-primitives", path = "../../substrate/in-instructions/primitives", default-features = false, features = ["std", "borsh"] }
 coins-primitives = { package = "serai-coins-primitives", path = "../../substrate/coins/primitives", default-features = false, features = ["std", "borsh"] }
 validator-sets-primitives = { package = "serai-validator-sets-primitives", path = "../../substrate/validator-sets/primitives", default-features = false, features = ["std", "borsh"] }
+
+serai-cosign = { path = "../../coordinator/cosign", default-features = false }

processor/messages/src/lib.rs

@@ -11,6 +11,8 @@ use validator_sets_primitives::{Session, KeyPair, Slash};
 use coins_primitives::OutInstructionWithBalance;
 use in_instructions_primitives::SignedBatch;
 
+use serai_cosign::{CosignIntent, SignedCosign};
+
 #[derive(Clone, Copy, PartialEq, Eq, Debug, BorshSerialize, BorshDeserialize)]
 pub struct SubstrateContext {
   pub serai_time: u64,
@@ -24,7 +26,7 @@ pub mod key_gen {
   pub enum CoordinatorMessage {
     /// Instructs the Processor to begin the key generation process.
     ///
-    /// This is sent by the Coordinator when it creates the Tributary (TODO).
+    /// This is sent by the Coordinator when it creates the Tributary.
     GenerateKey { session: Session, threshold: u16, evrf_public_keys: Vec<([u8; 32], Vec<u8>)> },
     /// Received participations for the specified key generation protocol.
     ///
@@ -50,7 +52,8 @@ pub mod key_gen {
     }
   }
 
-  #[derive(Clone, PartialEq, Eq, BorshSerialize, BorshDeserialize)]
+  // This set of messages is sent entirely and solely by serai-processor-key-gen.
+  #[derive(Clone, BorshSerialize, BorshDeserialize)]
   pub enum ProcessorMessage {
     // Participated in the specified key generation protocol.
     Participation { session: Session, participation: Vec<u8> },
@@ -141,7 +144,8 @@ pub mod sign {
     }
   }
 
-  #[derive(Clone, PartialEq, Eq, Debug, BorshSerialize, BorshDeserialize)]
+  // This set of messages is sent entirely and solely by serai-processor-frost-attempt-manager.
+  #[derive(Clone, Debug, BorshSerialize, BorshDeserialize)]
   pub enum ProcessorMessage {
     // Participant sent an invalid message during the sign protocol.
     InvalidParticipant { session: Session, participant: Participant },
@@ -155,39 +159,25 @@ pub mod sign {
 pub mod coordinator {
   use super::*;
 
-  // TODO: Remove this for the one defined in serai-cosign
-  pub fn cosign_block_msg(block_number: u64, block: [u8; 32]) -> Vec<u8> {
-    const DST: &[u8] = b"Cosign";
-    let mut res = vec![u8::try_from(DST.len()).unwrap()];
-    res.extend(DST);
-    res.extend(block_number.to_le_bytes());
-    res.extend(block);
-    res
-  }
-
   #[derive(Clone, PartialEq, Eq, Debug, BorshSerialize, BorshDeserialize)]
   pub enum CoordinatorMessage {
     /// Cosign the specified Substrate block.
     ///
     /// This is sent by the Coordinator's Tributary scanner.
-    CosignSubstrateBlock { session: Session, block_number: u64, block: [u8; 32] },
+    CosignSubstrateBlock { session: Session, intent: CosignIntent },
     /// Sign the slash report for this session.
     ///
     /// This is sent by the Coordinator's Tributary scanner.
     SignSlashReport { session: Session, report: Vec<Slash> },
   }
 
-  #[derive(Clone, PartialEq, Eq, Debug, BorshSerialize, BorshDeserialize)]
-  pub struct PlanMeta {
-    pub session: Session,
-    pub id: [u8; 32],
-  }
-
-  #[derive(Clone, PartialEq, Eq, Debug, BorshSerialize, BorshDeserialize)]
+  // This set of messages is sent entirely and solely by serai-processor-bin's implementation of
+  // the signers::Coordinator trait.
+  // TODO: Move message creation into serai-processor-signers
+  #[derive(Clone, Debug, BorshSerialize, BorshDeserialize)]
   pub enum ProcessorMessage {
-    CosignedBlock { block_number: u64, block: [u8; 32], signature: Vec<u8> },
+    CosignedBlock { cosign: SignedCosign },
     SignedBatch { batch: SignedBatch },
-    SubstrateBlockAck { block: u64, plans: Vec<PlanMeta> },
     SignedSlashReport { session: Session, signature: Vec<u8> },
   }
 }
@@ -213,17 +203,17 @@ pub mod substrate {
   pub enum CoordinatorMessage {
     /// Keys set on the Serai blockchain.
     ///
-    /// This is set by the Coordinator's Substrate canonical event stream.
+    /// This is sent by the Coordinator's Substrate canonical event stream.
     SetKeys { serai_time: u64, session: Session, key_pair: KeyPair },
     /// Slashes reported on the Serai blockchain OR the process timed out.
     ///
     /// This is the final message for a session,
     ///
-    /// This is set by the Coordinator's Substrate canonical event stream.
+    /// This is sent by the Coordinator's Substrate canonical event stream.
     SlashesReported { session: Session },
     /// A block from Serai with relevance to this processor.
     ///
-    /// This is set by the Coordinator's Substrate canonical event stream.
+    /// This is sent by the Coordinator's Substrate canonical event stream.
     Block {
       serai_block_number: u64,
       batch: Option<ExecutedBatch>,
@@ -231,17 +221,16 @@ pub mod substrate {
     },
   }
 
-  #[derive(Clone, PartialEq, Eq, Debug)]
-  pub enum ProcessorMessage {}
-  impl BorshSerialize for ProcessorMessage {
-    fn serialize<W: borsh::io::Write>(&self, _writer: &mut W) -> borsh::io::Result<()> {
-      unimplemented!()
-    }
-  }
-  impl BorshDeserialize for ProcessorMessage {
-    fn deserialize_reader<R: borsh::io::Read>(_reader: &mut R) -> borsh::io::Result<Self> {
-      unimplemented!()
+  #[derive(Clone, PartialEq, Eq, Debug, BorshSerialize, BorshDeserialize)]
+  pub struct PlanMeta {
+    pub session: Session,
+    pub transaction_plan_id: [u8; 32],
   }
+
+  #[derive(Clone, Debug, BorshSerialize, BorshDeserialize)]
+  pub enum ProcessorMessage {
+    // TODO: Have the processor send this
+    SubstrateBlockAck { block: [u8; 32], plans: Vec<PlanMeta> },
   }
 }
 
@@ -268,7 +257,7 @@ impl_from!(sign, CoordinatorMessage, Sign);
 impl_from!(coordinator, CoordinatorMessage, Coordinator);
 impl_from!(substrate, CoordinatorMessage, Substrate);
 
-#[derive(Clone, PartialEq, Eq, Debug, BorshSerialize, BorshDeserialize)]
+#[derive(Clone, Debug, BorshSerialize, BorshDeserialize)]
 pub enum ProcessorMessage {
   KeyGen(key_gen::ProcessorMessage),
   Sign(sign::ProcessorMessage),
@@ -331,8 +320,8 @@ impl CoordinatorMessage {
       CoordinatorMessage::Coordinator(msg) => {
         let (sub, id) = match msg {
           // We only cosign a block once, and Reattempt is a separate message
-          coordinator::CoordinatorMessage::CosignSubstrateBlock { block_number, .. } => {
-            (0, block_number.encode())
+          coordinator::CoordinatorMessage::CosignSubstrateBlock { intent, .. } => {
+            (0, intent.block_number.encode())
           }
           // We only sign one slash report, and Reattempt is a separate message
           coordinator::CoordinatorMessage::SignSlashReport { session, .. } => (1, session.encode()),
@@ -404,17 +393,26 @@ impl ProcessorMessage {
       }
       ProcessorMessage::Coordinator(msg) => {
         let (sub, id) = match msg {
-          coordinator::ProcessorMessage::CosignedBlock { block, .. } => (0, block.encode()),
+          coordinator::ProcessorMessage::CosignedBlock { cosign } => {
+            (0, cosign.cosign.block_hash.encode())
+          }
           coordinator::ProcessorMessage::SignedBatch { batch, .. } => (1, batch.batch.id.encode()),
-          coordinator::ProcessorMessage::SubstrateBlockAck { block, .. } => (2, block.encode()),
-          coordinator::ProcessorMessage::SignedSlashReport { session, .. } => (3, session.encode()),
+          coordinator::ProcessorMessage::SignedSlashReport { session, .. } => (2, session.encode()),
         };
 
         let mut res = vec![PROCESSOR_UID, TYPE_COORDINATOR_UID, sub];
         res.extend(&id);
         res
       }
-      ProcessorMessage::Substrate(_) => panic!("requesting intent for empty message type"),
+      ProcessorMessage::Substrate(msg) => {
+        let (sub, id) = match msg {
+          substrate::ProcessorMessage::SubstrateBlockAck { block, .. } => (0, block.encode()),
+        };
+
+        let mut res = vec![PROCESSOR_UID, TYPE_SUBSTRATE_UID, sub];
+        res.extend(&id);
+        res
+      }
     }
   }
 }

processor/scanner/src/batch/mod.rs

@@ -7,7 +7,10 @@ use serai_db::{DbTxn, Db};
 
 use serai_in_instructions_primitives::{MAX_BATCH_SIZE, Batch};
 
-use primitives::{EncodableG, task::ContinuallyRan};
+use primitives::{
+  EncodableG,
+  task::{DoesNotError, ContinuallyRan},
+};
 use crate::{
   db::{Returnable, ScannerGlobalDb, InInstructionData, ScanToBatchDb, BatchData, BatchToReportDb},
   index,
@@ -60,7 +63,9 @@ impl<D: Db, S: ScannerFeed> BatchTask<D, S> {
 }
 
 impl<D: Db, S: ScannerFeed> ContinuallyRan for BatchTask<D, S> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = DoesNotError;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       let highest_batchable = {
         // Fetch the next to scan block

processor/scanner/src/eventuality/mod.rs

@@ -190,7 +190,9 @@ impl<D: Db, S: ScannerFeed, Sch: Scheduler<S>> EventualityTask<D, S, Sch> {
 }
 
 impl<D: Db, S: ScannerFeed, Sch: Scheduler<S>> ContinuallyRan for EventualityTask<D, S, Sch> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = String;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       // Fetch the highest acknowledged block
       let Some(highest_acknowledged) = ScannerGlobalDb::<S>::highest_acknowledged_block(&self.db)

processor/scanner/src/index/mod.rs

@@ -58,7 +58,9 @@ impl<D: Db, S: ScannerFeed> IndexTask<D, S> {
 }
 
 impl<D: Db, S: ScannerFeed> ContinuallyRan for IndexTask<D, S> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = String;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       // Fetch the latest finalized block
       let our_latest_finalized = IndexDb::latest_finalized_block(&self.db)

processor/scanner/src/report/mod.rs

@@ -4,7 +4,7 @@ use serai_db::{DbTxn, Db};
 
 use serai_validator_sets_primitives::Session;
 
-use primitives::task::ContinuallyRan;
+use primitives::task::{DoesNotError, ContinuallyRan};
 use crate::{
   db::{BatchData, BatchToReportDb, BatchesToSign},
   substrate, ScannerFeed,
@@ -27,7 +27,9 @@ impl<D: Db, S: ScannerFeed> ReportTask<D, S> {
 }
 
 impl<D: Db, S: ScannerFeed> ContinuallyRan for ReportTask<D, S> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = DoesNotError;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       let mut made_progress = false;
       loop {

processor/scanner/src/scan/mod.rs

@@ -98,7 +98,9 @@ impl<D: Db, S: ScannerFeed> ScanTask<D, S> {
 }
 
 impl<D: Db, S: ScannerFeed> ContinuallyRan for ScanTask<D, S> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = String;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       // Fetch the safe to scan block
       let latest_scannable =

processor/scanner/src/substrate/mod.rs

@@ -5,7 +5,7 @@ use serai_db::{Get, DbTxn, Db};
 use serai_coins_primitives::{OutInstruction, OutInstructionWithBalance};
 
 use messages::substrate::ExecutedBatch;
-use primitives::task::ContinuallyRan;
+use primitives::task::{DoesNotError, ContinuallyRan};
 use crate::{
   db::{ScannerGlobalDb, SubstrateToEventualityDb, AcknowledgedBatches},
   index, batch, ScannerFeed, KeyFor,
@@ -50,7 +50,9 @@ impl<D: Db, S: ScannerFeed> SubstrateTask<D, S> {
 }
 
 impl<D: Db, S: ScannerFeed> ContinuallyRan for SubstrateTask<D, S> {
-  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, String>> {
+  type Error = DoesNotError;
+
+  fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       let mut made_progress = false;
       loop {