Merge pull request #69 from floor-licker/fix/public-book-snapshot-clocks

fix: expose book snapshot clocks

README.md

@@ -78,6 +78,8 @@ Run the WS hot-path benchmark locally with `cargo bench --bench ws_hot_path`.
 
 **Parsing paths:** `polyfill-rs` keeps two parsing layers on purpose. The allocation-sensitive WS `book` path uses `WsBookUpdateProcessor` in `src/ws_hot_path.rs`, which walks a reusable `simd-json` tape and applies fixed-point book levels directly. The generic stream parser in `src/decode.rs` is an ergonomic compatibility path: it parses through `serde_json::Value` so it can tolerate batches, unknown event types, and mixed message shapes. Likewise, several generic numeric/decimal deserializers in `src/decode.rs` accept string-or-number API fields through `serde_json::Value`; they are not the zero-allocation hot path.
 
+**WebSocket snapshot ordering:** Polymarket `book` messages expose a millisecond `timestamp` and optional `hash`, but no monotonic server sequence/version. The book applier treats newer timestamps as newer, rejects older timestamps, suppresses exact same-timestamp/same-hash duplicates, and accepts same-timestamp/different-hash snapshots in websocket arrival order. The hash distinguishes duplicate vs distinct state; it is not a logical ordering key.
+
 **Key Performance Optimizations:**
 
 The 21.4% performance improvement comes from HTTP/2 tuning with 512KB stream windows optimized for 469KB payloads, explicit Polymarket request headers, SIMD-backed parsing where the client uses the typed fast-response helper for large REST market responses, and opt-in connection prewarming/keep-alive support.

src/book.rs

@@ -460,6 +460,8 @@ impl OrderBook {
             bids: self.bids(None), // Get all bids (up to max_depth)
             asks: self.asks(None), // Get all asks (up to max_depth)
             sequence: self.last_delta_sequence,
+            last_delta_sequence: self.last_delta_sequence,
+            last_snapshot_timestamp_ms: self.last_snapshot_timestamp_ms,
         }
     }
 
@@ -599,9 +601,10 @@ impl OrderBook {
             return Err(PolyfillError::validation("Token ID mismatch"));
         }
 
-        // Use the exchange-provided timestamp as the monotonic snapshot marker.
+        // Use the exchange-provided timestamp as the primary snapshot marker. The WS `book`
-        // If the feed emits two snapshots in the same millisecond, a different hash is treated as
+        // message does not expose a monotonic server sequence/version, so same-millisecond
-        // a distinct newer state. Equal timestamp without a hash is considered duplicate/stale.
+        // snapshots with different hashes are ordered by websocket arrival order. The hash
+        // distinguishes duplicate vs distinct state; it is not a logical ordering key.
         // Snapshot timestamps are intentionally separate from legacy delta sequence numbers.
         if !self.should_apply_snapshot(update.timestamp, update.hash.as_deref()) {
             return Ok(());
@@ -723,6 +726,8 @@ impl OrderBook {
 
     #[inline]
     fn should_apply_snapshot(&self, timestamp: u64, hash: Option<&str>) -> bool {
+        // Without a server sequence/version, equal-timestamp distinct hashes can only be ordered
+        // by arrival. Older timestamps are always stale; exact same timestamp/hash is duplicate.
         if timestamp > self.last_snapshot_timestamp_ms {
             return true;
         }
@@ -1526,6 +1531,11 @@ mod tests {
         assert_eq!(book.last_snapshot_timestamp_ms, 1_000);
         assert_eq!(book.best_bid().unwrap().price, dec!(0.50));
         assert_eq!(book.best_ask().unwrap().price, dec!(0.60));
+
+        let snapshot = book.snapshot();
+        assert_eq!(snapshot.sequence, 10_000);
+        assert_eq!(snapshot.last_delta_sequence, 10_000);
+        assert_eq!(snapshot.last_snapshot_timestamp_ms, 1_000);
     }
 
     #[test]

src/decode.rs

@@ -341,6 +341,8 @@ impl Decoder<OrderBook> for RawOrderBookResponse {
             bids,
             asks,
             sequence: 0, // TODO: Get from response if available
+            last_delta_sequence: 0,
+            last_snapshot_timestamp_ms: 0,
         })
     }
 }

src/types.rs

@@ -358,7 +358,7 @@ impl FastBookLevel {
 }
 
 /// Full order book state
-#[derive(Debug, Clone, Serialize, Deserialize)]
+#[derive(Debug, Clone, Serialize)]
 pub struct OrderBook {
     /// Token ID
     pub token_id: String,
@@ -368,8 +368,47 @@ pub struct OrderBook {
     pub bids: Vec<BookLevel>,
     /// Ask orders
     pub asks: Vec<BookLevel>,
-    /// Sequence number
+    /// Legacy/incremental delta sequence number.
+    ///
+    /// This is kept for compatibility. For snapshots produced by this client,
+    /// it is equivalent to [`Self::last_delta_sequence`]. WebSocket snapshot
+    /// timestamps are exposed separately in [`Self::last_snapshot_timestamp_ms`].
     pub sequence: u64,
+    /// Last accepted legacy/incremental delta sequence number.
+    pub last_delta_sequence: u64,
+    /// Last accepted full-book snapshot timestamp in milliseconds.
+    pub last_snapshot_timestamp_ms: u64,
+}
+
+impl<'de> Deserialize<'de> for OrderBook {
+    fn deserialize<D>(deserializer: D) -> std::result::Result<Self, D::Error>
+    where
+        D: serde::Deserializer<'de>,
+    {
+        #[derive(Deserialize)]
+        struct WireOrderBook {
+            token_id: String,
+            timestamp: DateTime<Utc>,
+            bids: Vec<BookLevel>,
+            asks: Vec<BookLevel>,
+            sequence: u64,
+            #[serde(default)]
+            last_delta_sequence: Option<u64>,
+            #[serde(default)]
+            last_snapshot_timestamp_ms: Option<u64>,
+        }
+
+        let wire = WireOrderBook::deserialize(deserializer)?;
+        Ok(Self {
+            token_id: wire.token_id,
+            timestamp: wire.timestamp,
+            bids: wire.bids,
+            asks: wire.asks,
+            sequence: wire.sequence,
+            last_delta_sequence: wire.last_delta_sequence.unwrap_or(wire.sequence),
+            last_snapshot_timestamp_ms: wire.last_snapshot_timestamp_ms.unwrap_or_default(),
+        })
+    }
 }
 
 /// Order book delta for streaming updates - EXTERNAL API VERSION
@@ -937,16 +976,26 @@ pub enum StreamMessage {
 }
 
 /// Orderbook update message (full snapshot or delta).
+///
+/// WebSocket `book` messages expose a millisecond timestamp and optional book hash, but no
+/// monotonic server sequence/version. Same-timestamp messages with different hashes are therefore
+/// ordered by websocket arrival order by the book applier; the hash is a duplicate/state
+/// discriminator, not a logical ordering key.
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct BookUpdate {
     pub asset_id: String,
     pub market: String,
+    /// Exchange-provided snapshot timestamp in milliseconds.
     #[serde(deserialize_with = "crate::decode::deserializers::number_from_string")]
     pub timestamp: u64,
     #[serde(deserialize_with = "crate::decode::deserializers::vec_from_null")]
     pub bids: Vec<OrderSummary>,
     #[serde(deserialize_with = "crate::decode::deserializers::vec_from_null")]
     pub asks: Vec<OrderSummary>,
+    /// Exchange-provided snapshot hash.
+    ///
+    /// Used to suppress exact duplicate same-timestamp snapshots and to allow distinct
+    /// same-timestamp states. It does not encode ordering.
     #[serde(default)]
     pub hash: Option<String>,
 }
@@ -1922,4 +1971,20 @@ mod tests {
             Decimal::from_str("0.00005").unwrap()
         ));
     }
+
+    #[test]
+    fn order_book_snapshot_clocks_default_for_legacy_payloads() {
+        let json = r#"{
+            "token_id":"test_token",
+            "timestamp":"2026-06-23T00:00:00Z",
+            "bids":[],
+            "asks":[],
+            "sequence":42
+        }"#;
+
+        let book: OrderBook = serde_json::from_str(json).unwrap();
+        assert_eq!(book.sequence, 42);
+        assert_eq!(book.last_delta_sequence, 42);
+        assert_eq!(book.last_snapshot_timestamp_ms, 0);
+    }
 }

src/ws_hot_path.rs

@@ -385,6 +385,8 @@ mod tests {
 
         let snapshot = books.get_book("test_asset_id").unwrap();
         assert_eq!(snapshot.sequence, 0);
+        assert_eq!(snapshot.last_delta_sequence, 0);
+        assert_eq!(snapshot.last_snapshot_timestamp_ms, 1000);
         assert_eq!(snapshot.timestamp.timestamp_millis(), 1000);
         assert_eq!(snapshot.bids.len(), 1);
         assert_eq!(snapshot.asks.len(), 1);
@@ -423,6 +425,8 @@ mod tests {
 
         let snapshot = books.get_book("test_asset_id").unwrap();
         assert_eq!(snapshot.sequence, 0);
+        assert_eq!(snapshot.last_delta_sequence, 0);
+        assert_eq!(snapshot.last_snapshot_timestamp_ms, 1000);
         assert_eq!(snapshot.timestamp.timestamp_millis(), 1000);
         assert_eq!(snapshot.bids.len(), 1);
         assert_eq!(snapshot.asks.len(), 1);
@@ -450,6 +454,8 @@ mod tests {
 
         let snapshot = books.get_book("test_asset_id").unwrap();
         assert_eq!(snapshot.sequence, 0);
+        assert_eq!(snapshot.last_delta_sequence, 0);
+        assert_eq!(snapshot.last_snapshot_timestamp_ms, 1000);
         assert_eq!(snapshot.timestamp.timestamp_millis(), 1000);
         assert_eq!(snapshot.bids[0].price, dec!(0.51));
         assert_eq!(snapshot.bids[0].size, dec!(11));