@aztec/p2p 0.0.1-commit.f504929 → 0.0.1-commit.f650c0a5c

package/src/services/peer-manager/peer_scoring.ts

@@ -1,5 +1,6 @@
 import { median } from '@aztec/foundation/collection';
 import { createLogger } from '@aztec/foundation/log';
+import { DateProvider } from '@aztec/foundation/timer';
 import { PeerErrorSeverity } from '@aztec/stdlib/p2p';
 import {
   Attributes,
@@ -54,6 +55,7 @@ export enum PeerScoreState {
 // TODO: move into config / constants
 const MIN_SCORE_BEFORE_BAN = -100;
 const MIN_SCORE_BEFORE_DISCONNECT = -50;
+const SCORE_CLEANUP_THRESHOLD = 0.1;
 
 export class PeerScoring {
   private logger = createLogger('p2p:peer-scoring');
@@ -65,7 +67,11 @@ export class PeerScoring {
 
   private peerStateCounter: UpDownCounter;
 
-  constructor(config: P2PConfig, telemetry: TelemetryClient = getTelemetryClient()) {
+  constructor(
+    config: P2PConfig,
+    telemetry: TelemetryClient = getTelemetryClient(),
+    private readonly dateProvider: DateProvider = new DateProvider(),
+  ) {
     const orderedValues = config.peerPenaltyValues?.sort((a, b) => a - b);
     this.peerPenalties = {
       [PeerErrorSeverity.HighToleranceError]:
@@ -92,7 +98,7 @@ export class PeerScoring {
   }
 
   updateScore(peerId: string, scoreDelta: number): number {
-    const currentTime = Date.now();
+    const currentTime = this.dateProvider.now();
     const lastUpdate = this.lastUpdateTime.get(peerId) || currentTime;
     const timePassed = currentTime - lastUpdate;
     const decayPeriods = Math.floor(timePassed / this.decayInterval);
@@ -111,19 +117,35 @@ export class PeerScoring {
   }
 
   decayAllScores(): void {
-    const currentTime = Date.now();
+    const currentTime = this.dateProvider.now();
     for (const [peerId, lastUpdate] of this.lastUpdateTime.entries()) {
       const timePassed = currentTime - lastUpdate;
       const decayPeriods = Math.floor(timePassed / this.decayInterval);
       if (decayPeriods > 0) {
         let score = this.scores.get(peerId) || 0;
         score *= Math.pow(this.decayFactor, decayPeriods);
-        this.scores.set(peerId, score);
-        this.lastUpdateTime.set(peerId, currentTime);
+        if (Math.abs(score) < SCORE_CLEANUP_THRESHOLD) {
+          this.scores.delete(peerId);
+          this.lastUpdateTime.delete(peerId);
+        } else {
+          this.scores.set(peerId, score);
+          this.lastUpdateTime.set(peerId, currentTime);
+        }
       }
     }
   }
 
+  /** Resets all peer scores. Useful for benchmarks to prevent cross-case contamination. */
+  resetAllScores(): void {
+    this.scores.clear();
+    this.lastUpdateTime.clear();
+  }
+
+  removePeer(peerId: string): void {
+    this.scores.delete(peerId);
+    this.lastUpdateTime.delete(peerId);
+  }
+
   getScore(peerId: string): number {
     return this.scores.get(peerId) || 0;
   }

package/src/services/reqresp/README.md

@@ -0,0 +1,229 @@
+# ReqResp Protocols
+
+This module implements libp2p request-response protocols for the Aztec P2P network. All protocols share common transport-level validation (rate limiting, timeouts, Snappy decompression, error penalties) with protocol-specific logic layered on top.
+
+## Common Transport Validation
+
+### Rate Limiting (Responder Side)
+
+Applied before the protocol handler runs.
+
+| Protocol | Peer Limit | Global Limit | File |
+|----------|-----------|-------------|------|
+| PING | 5/s | 10/s | `rate-limiter/rate_limits.ts` |
+| STATUS | 5/s | 10/s | same |
+| AUTH | 5/s | 10/s | same |
+| GOODBYE | 5/s | 10/s | same |
+| BLOCK | 2/s | 5/s | same |
+| BLOCK_TXS | 10/s | 200/s | same |
+| TX | (see rate limits file) | (see rate limits file) | same |
+
+- Per-peer limit exceeded: `HighToleranceError` penalty + `RATE_LIMIT_EXCEEDED` status. Penalty fires inside `RequestResponseRateLimiter.allow()`, not the stream handler.
+- Global limit exceeded: `RATE_LIMIT_EXCEEDED` status only (no peer penalty).
+
+### Response Status Byte (Requester Side)
+
+| Rule | Consequence | File |
+|------|-------------|------|
+| First chunk must be exactly 1 byte | `ReqRespStatusError(UNKNOWN)` | `status.ts` |
+| Byte must be valid `ReqRespStatus` enum (0-4, 126, 127) | `ReqRespStatusError(UNKNOWN)` | same |
+
+Note: `prettyPrintReqRespStatus` is missing a `NOT_FOUND` case (minor logging bug).
+
+### Snappy Decompression (Requester Side)
+
+Per-protocol size limits checked via preamble before decompression.
+
+### Timeouts (Requester Side)
+
+| Timeout | Default | Penalty |
+|---------|---------|---------|
+| Individual request | 10s | HighToleranceError |
+| Dial | 5s | HighToleranceError |
+
+### Error Penalty Categorization (Requester Side)
+
+| Error Type | Severity |
+|------------|----------|
+| GOODBYE subprotocol errors | None |
+| `CollectiveReqRespTimeoutError` / `InvalidResponseError` | None |
+| `AbortError` / connection close / muxer closed | None |
+| `ECONNRESET` / `EPIPE` / `ECONNREFUSED` / `ERR_UNEXPECTED_EOF` | HighToleranceError |
+| `ERR_UNSUPPORTED_PROTOCOL` | HighToleranceError |
+| `IndividualReqRespTimeoutError` / `TimeoutError` | HighToleranceError |
+| Catch-all | HighToleranceError |
+
+### Request Error Penalty (Responder Side)
+
+| Error Type | Severity |
+|------------|----------|
+| `BADLY_FORMED_REQUEST` | LowToleranceError |
+| All others | None |
+
+### Notes
+
+- Request payloads are NOT snappy-compressed (asymmetric: only responses use snappy).
+
+---
+
+## Handshake Protocols
+
+### Connection-Level Gating (Before Any Handshake)
+
+| Rule | Consequence | File |
+|------|-------------|------|
+| Deny inbound connection from IP/peerId with too many failed auth handshakes | Connection denied | `libp2p_service.ts` |
+| Threshold: `p2pMaxFailedAuthAttemptsAllowed` (default 3) | Tracked per peerId AND per IP | `peer_manager.ts` |
+| Failed auth entries expire after 1 hour | Peer can reconnect; no escalating penalty for repeat offenders | same |
+
+### Handshake Trigger Logic (`peer:connect`)
+
+1. `p2pDisableStatusHandshake` = true: no handshake
+2. `p2pAllowOnlyValidators` = false: STATUS handshake
+3. Peer is protected (trusted/private/preferred): STATUS handshake
+4. Otherwise: AUTH handshake (superset of STATUS)
+
+Config constraint: `p2pDisableStatusHandshake && p2pAllowOnlyValidators` is disallowed.
+
+### STATUS Protocol (`/aztec/req/status/1.0.0`)
+
+**Requester side** (`peer_manager.ts`):
+
+| Rule | Consequence |
+|------|-------------|
+| Response status must be SUCCESS | Peer scheduled for disconnect |
+| `compressedComponentsVersion` must match | Peer scheduled for disconnect |
+| Any exception | Peer scheduled for disconnect |
+
+`StatusMessage.validate()` currently only checks `compressedComponentsVersion`. Fields `latestBlockNumber`, `latestBlockHash`, `finalizedBlockNumber` are NOT validated (TODO in code).
+
+**Responder side**: no validation of incoming request content (always responds with own status). This means the requester leaks its blockchain state to any peer before validation.
+
+**Deserialization bounds**: `MAX_VERSION_STRING_LENGTH` = 64 bytes, `MAX_BLOCK_HASH_STRING_LENGTH` = 128 bytes. Expected response size: 1 KB.
+
+### AUTH Protocol (`/aztec/req/auth/1.0.0`)
+
+**Requester side** (`peer_manager.ts`):
+
+| # | Rule | Consequence |
+|---|------|-------------|
+| 1 | Response status is SUCCESS | `markAuthHandshakeFailed` + disconnect |
+| 2 | `compressedComponentsVersion` match | `markAuthHandshakeFailed` + disconnect |
+| 3 | Valid ECDSA signature recovery from challenge response | `markAuthHandshakeFailed` + disconnect |
+| 4 | Recovered address is a registered validator | `markAuthHandshakeFailed` + disconnect |
+| 5 | Validator address not already authenticated to different peerId | Silent return (no disconnect, no failure marking -- peer stays connected but unauthenticated) |
+| 6 | Any exception | `markAuthHandshakeFailed` + disconnect |
+
+Challenge: random `Fr`, payload = `keccak256("Aztec Validator Challenge:" + challenge)`, signed with `eth_sign` style. Challenge is NOT bound to peer identity (transport encryption via Noise is the binding layer).
+
+On success: peer added to authenticated maps, prior failures cleared (including IP-based ones -- shared-IP peers benefit from a legitimate validator's success).
+
+**Responder side** (`validator-client/src/validator.ts` + `peer_manager.ts`):
+
+| # | Rule | Consequence |
+|---|------|-------------|
+| 1 | Peer must be protected (`shouldTrustWithIdentity` in `peer_manager.ts`) | Returns empty buffer (SUCCESS status + empty payload -> requester gets parse error -> `markAuthHandshakeFailed`) |
+| 2 | Node must have registered validator address | Returns empty buffer (same consequence) |
+
+**Unauthenticated peer gossip**: when `p2pAllowOnlyValidators` is true, unauthenticated peers get `appSpecificScore = -Infinity`, completely excluding them from all gossip.
+
+### PING Protocol (`/aztec/req/ping/1.0.0`)
+
+No validation on either side. Responder returns `Buffer.from('pong')`. Expected response: 1 KB.
+
+### GOODBYE Protocol (`/aztec/req/goodbye/1.0.0`)
+
+**Responder**: buffer must be 1 byte (defaults to `UNKNOWN` on invalid length). Goodbye reason byte is NOT validated against the enum -- any byte 0-255 accepted. Peer scheduled for disconnect regardless of reason.
+
+**Requester**: response errors are never penalized (GOODBYE subprotocol exempt from error categorization).
+
+### Periodic Re-validation
+
+| Rule | Interval | File |
+|------|----------|------|
+| Authenticated validators re-checked against current validator set | Every heartbeat (`peerCheckIntervalMS`) | `peer_manager.ts` |
+| If validator address no longer registered, auth entry removed | Same | same |
+
+Protected peers (private/trusted/preferred) are always considered "authenticated" without AUTH handshake.
+
+---
+
+## Block Data Protocols
+
+### BLOCK Protocol (`/aztec/req/block/1.0.0`)
+
+**Server side**:
+
+| Rule | Consequence | File |
+|------|-------------|------|
+| Request must parse as `Fr` | `BADLY_FORMED_REQUEST` + LowToleranceError | `protocols/block.ts` |
+| Block lookup throws | `INTERNAL_ERROR` status | same |
+| Block not found | SUCCESS + empty buffer (design choice; no `NOT_FOUND` status used) | same |
+
+**Requester side** (Snappy limit: 3 MB):
+
+| Rule | Consequence | File |
+|------|-------------|------|
+| Response block number must match requested | LowToleranceError; rejected | `libp2p_service.ts` (`validateRequestedBlock`) |
+| Local block must exist for hash verification | Rejected (no penalty) | same |
+| Response block hash must equal local block hash | MidToleranceError; rejected | same |
+
+**Limitation**: the local-block requirement means BLOCK req/resp is unusable for initial P2P-only sync (before L1 sync provides local copies for verification). A TODO in the code acknowledges this.
+
+### BLOCK_TXS Protocol (`/aztec/req/block_txs/1.0.0`)
+
+**Server side**:
+
+| Rule | Consequence | File |
+|------|-------------|------|
+| Request must parse as `BlockTxsRequest` (Fr + TxHashArray + BitVector) | `BADLY_FORMED_REQUEST` + LowToleranceError | `protocols/block_txs/block_txs_handler.ts` |
+| BitVector length: non-negative and <= `MAX_TXS_PER_BLOCK` (65536) | Deserialization throws -> `BADLY_FORMED_REQUEST` | `protocols/block_txs/bitvector.ts` |
+| Archive root not found and no explicit txHashes | `NOT_FOUND` status | handler |
+| Internal error during lookup | Unhandled exception -> stream abort (no `INTERNAL_ERROR` status, unlike BLOCK) | handler |
+
+Conditional registration: BLOCK_TXS handler only registered when `config.disableTransactions` is false. Otherwise peers get `ERR_UNSUPPORTED_PROTOCOL`.
+
+**Requester side via `sendBatchRequest`** (Snappy limit: `max(N, 1) * 512 + 1` KB):
+
+| Rule | Consequence | File |
+|------|-------------|------|
+| Archive root must match request | MidToleranceError | `libp2p_service.ts` (`validateRequestedBlockTxs`) |
+| BitVector length must match request | MidToleranceError | same |
+| No duplicate tx hashes | MidToleranceError | same |
+| Tx count within bounds | MidToleranceError | same |
+| Local block proposal must exist for archive root | Rejected (no penalty) | same |
+| All tx hashes must be in proposal's tx list at allowed indices | LowToleranceError | same |
+| Txs in strictly increasing index order | LowToleranceError | same |
+| Each tx passes well-formedness (Metadata [4 fields], Size, Data, Proof) | LowToleranceError | same |
+
+**Requester side via `BatchTxRequester`** (separate validation path):
+
+| Rule | Consequence | File |
+|------|-------------|------|
+| Non-SUCCESS status: `FAILURE`/`UNKNOWN` | HighToleranceError + "bad peer" tracking | `batch-tx-requester/batch_tx_requester.ts` |
+| `RATE_LIMIT_EXCEEDED` | Peer marked rate-limited (cooldown) | same |
+| `NOT_FOUND` / `BADLY_FORMED_REQUEST` / `INTERNAL_ERROR` | Falls through silently (no penalty) | same |
+| Each tx validated (Metadata + Size + Data + Proof) | LowToleranceError per invalid tx; valid txs from same response still accepted | same |
+| Archive root match + non-empty txIndices | No penalty on mismatch; peer not promoted to "smart" | same |
+
+**Double penalty on transport errors**: when `BatchTxRequester` encounters a transport error (e.g., ECONNRESET), both `sendRequestToPeer`'s internal handler and the `BatchTxRequester`'s catch block penalize the peer, resulting in double HighToleranceError.
+
+See [BatchTxRequester README](batch-tx-requester/README.md) for the full architecture (peer classification, worker model, wire protocol).
+
+### TX Protocol (`/aztec/req/tx/1.0.0`)
+
+**Server side**:
+
+| Rule | Consequence | File |
+|------|-------------|------|
+| Request must parse as `TxHashArray` | `BADLY_FORMED_REQUEST` + LowToleranceError | `protocols/tx.ts` |
+
+**Requester side** (validator registered at startup, not the default noop):
+
+| Rule | Consequence | File |
+|------|-------------|------|
+| Each returned tx hash must be in the requested set | MidToleranceError | `libp2p_service.ts` (`validateRequestedTxs`) |
+| Each tx passes well-formedness (Metadata + Size + Data + Proof) | LowToleranceError | same |
+
+Snappy limit: `max(N, 1) * 512 + 1` KB.
+

package/src/services/reqresp/batch-tx-requester/README.md

@@ -170,6 +170,37 @@ class BlockTxsResponse {
 
 The `BitVector` is a compact representation where each bit corresponds to a transaction index in the block proposal. This allows efficient capability advertisement without repeating full hashes.
 
+## Cancellation
+
+All cancellation is managed by a single `RequestTracker` instance, shared across the entire collection
+flow. The `RequestTracker` owns the deadline, tracks which txs are still missing, and exposes a
+`cancellationToken` promise that resolves when the request should stop (deadline hit, all txs fetched,
+or external `cancel()` call).
+
+Cancellation propagates from the deepest stack level upward:
+
+```
+RequestTracker.finish()
+  ├── resolves cancellationToken promise
+  │
+  ├── BatchTxRequester workers (deepest)
+  │     ├── shouldStop() checks requestTracker.cancelled → exit loop
+  │     ├── sleepClampedToDeadline races sleep vs cancellationToken → wakes
+  │     └── semaphore.acquire races vs cancellationToken → wakes
+  │           │
+  │           ▼ workers settle → txQueue.end() → generator returns
+  │
+  ├── Node collection loops
+  │     ├── notFinished() checks requestTracker.cancelled → exit loop
+  │     └── inter-retry sleep races vs cancellationToken → wakes
+  │           │
+  │           ▼ all node loops settle
+  │
+  └── collectFast (outermost)
+        awaits Promise.allSettled([reqresp, nodes]) → settles after inner tasks
+        finally: requestTracker.cancel() (idempotent), cleanup
+```
+
 ## Key Files
 
 | File | Description |
@@ -179,15 +210,16 @@ The `BitVector` is a compact representation where each bit corresponds to a tran
 | `peer_collection.ts` | Manages peer classification (dumb/smart/bad) and rate limiting |
 | `interface.ts` | Type definitions for dependencies |
 | `../protocols/block_txs/` | Wire protocol definitions (`BlockTxsRequest`, `BlockTxsResponse`, `BitVector`) |
+| `../../tx_collection/request_tracker.ts` | Centralized deadline, missing tx tracking, and cancellation signal |
 
 ## Stopping Conditions
 
-The `BatchTxRequester` stops when any of these conditions are met:
+The `BatchTxRequester` stops when any of these conditions are met, all managed by the `RequestTracker`:
 
-1. **All transactions fetched** - Success!
-2. **Deadline exceeded** - Timeout configured by caller
-3. **Abort signal** - External cancellation
-4. **No transactions to fetch** - Nothing was missing
+1. **All transactions fetched** - `markFetched()` removes the last missing tx, triggering `finish()`
+2. **Deadline exceeded** - `setTimeout` in `RequestTracker` fires, triggering `finish()`
+3. **External cancellation** - `RequestTracker.cancel()` called (e.g., from `stop()`, `stopCollectingForBlocksUpTo`)
+4. **No transactions to fetch** - Empty hash set at construction, `RequestTracker` finishes immediately
 
 ## Configuration
 
@@ -228,11 +260,15 @@ Request to peer fails
 ## Usage Example
 
 ```typescript
+const requestTracker = RequestTracker.create(
+  missingTxHashes,                          // TxHash[] - what we need
+  new Date(Date.now() + 5_000),             // deadline
+);
+
 const requester = new BatchTxRequester(
-  missingTxHashes,      // TxHash[] - what we need
+  requestTracker,       // IRequestTracker - tracks missing txs, deadline, and cancellation
   blockTxsSource,       // BlockTxsSource - the proposal or block we need txs for
   pinnedPeer,           // PeerId | undefined - peer expected to have the txs
-  timeoutMs,            // number - how long to try
   p2pService,           // BatchTxRequesterLibP2PService
 );
 
@@ -273,6 +309,8 @@ const txs = await BatchTxRequester.collectAllTxs(requester.run());
 │  1. Try RPC nodes first (fast)    │   │  Periodic polling of RPC nodes      │
 │  2. Fall back to BatchTxRequester │   │  and peers for missing txs          │
 │                                   │   │                                     │
+│  Creates RequestTracker per       │   │                                     │
+│  request with deadline            │   │                                     │
 └───────────────────┬───────────────┘   └─────────────────────────────────────┘
                     │
                     │ For 'proposal' and 'block' requests
@@ -281,6 +319,7 @@ const txs = await BatchTxRequester.collectAllTxs(requester.run());
 │                           BatchTxRequester                                  │
 │                                                                             │
 │  Aggressive parallel fetching from multiple peers                           │
+│  Shares RequestTracker with FastTxCollection for unified cancellation       │
 │  Uses BLOCK_TXS sub-protocol for efficient batching                         │
 └───────────────────┬─────────────────────────────────────────────────────────┘
                     │