fix(node): bound replay of authenticated gossip ref-update events

crates/gitlawb-core/src/http_sig.rs

@@ -113,15 +113,48 @@ impl HttpSignature {
         })
     }
 
-    /// Reject if the `created` timestamp is more than 5 minutes from now.
+    /// Reject a `created` timestamp outside the acceptance window, which is
+    /// ASYMMETRIC: up to 5 minutes into the past, but only 60 seconds into the
+    /// future.
+    ///
+    /// The two directions are two comparisons rather than one distance, because
+    /// they are not the same event. A signature that arrives late is ordinary:
+    /// clocks run slow, requests queue, and networks are not instant, so the
+    /// past side keeps the full 300-second allowance. A signature stamped ahead
+    /// of this node's clock is not ordinary, and folding both sides into an
+    /// `abs()` let a signer extend its own validity: signed at T with
+    /// `created = T + 300`, it stayed acceptable until roughly T + 600, so the
+    /// effective window was double the one this function advertises. The
+    /// forward tolerance exists only to absorb honest drift between two hosts,
+    /// which is what 60 seconds buys; it is the same allowance the gossip
+    /// path's freshness check uses for the same reason.
     pub fn check_created(&self) -> Result<()> {
+        const MAX_AGE_SECS: i64 = 300;
+        const MAX_FUTURE_SECS: i64 = 60;
+
         let now = Utc::now().timestamp();
-        let skew = (now - self.created).abs();
-        if skew > 300 {
+
+        // Saturating, not plain subtraction. `created` is parsed as an
+        // unrestricted i64 straight from the Signature-Input header, so a
+        // sender picks it: at i64::MIN the past-side subtraction overflows,
+        // which panics a debug build and wraps a release one into an absurd
+        // value that can read as acceptable. Saturating gives the answer the
+        // check wants at both extremes, since a timestamp that far away is
+        // refused by whichever side it saturates toward.
+        let age = now.saturating_sub(self.created);
+        if age > MAX_AGE_SECS {
+            return Err(Error::HttpSignature(format!(
+                "clock skew too large: created {age}s in the past (max {MAX_AGE_SECS}s)"
+            )));
+        }
+
+        let ahead = self.created.saturating_sub(now);
+        if ahead > MAX_FUTURE_SECS {
             return Err(Error::HttpSignature(format!(
-                "clock skew too large: {skew}s (max 300s)"
+                "clock skew too large: created {ahead}s in the future (max {MAX_FUTURE_SECS}s)"
             )));
         }
+
         Ok(())
     }
 
@@ -335,6 +368,75 @@ mod tests {
         assert!(sig.check_created().is_err());
     }
 
+    /// Build a parseable signature whose `created` is `offset` seconds from now
+    /// (negative for the past), so a test can pin one side of the window.
+    fn sig_created_at_offset(offset: i64) -> HttpSignature {
+        let kp = Keypair::generate();
+        let did = kp.did();
+        let created = Utc::now().timestamp() + offset;
+        let sig_input = format!(
+            r#"sig1=("@method" "@path" "content-digest");keyid="{did}";alg="ed25519";created={created}"#
+        );
+        HttpSignature::parse(&sig_input, "sig1=:AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA:").unwrap()
+    }
+
+    /// Build a signature at an ABSOLUTE `created`, so a test can drive the
+    /// extremes an offset from now cannot reach.
+    fn sig_created_absolute(created: i64) -> HttpSignature {
+        let kp = Keypair::generate();
+        let did = kp.did();
+        let sig_input = format!(
+            r#"sig1=("@method" "@path" "content-digest");keyid="{did}";alg="ed25519";created={created}"#
+        );
+        HttpSignature::parse(&sig_input, "sig1=:AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA:").unwrap()
+    }
+
+    /// `created` is parsed as an unrestricted i64 from a header the sender
+    /// writes, so the window check has to survive both ends of the type. Before
+    /// the saturating form this panicked with "attempt to subtract with
+    /// overflow" on the past side, which is a debug-build crash any client
+    /// could trigger by sending one header value.
+    #[test]
+    fn extreme_created_values_are_refused_rather_than_overflowing() {
+        for created in [i64::MIN, i64::MIN + 1, i64::MAX - 1, i64::MAX] {
+            let err = sig_created_absolute(created)
+                .check_created()
+                .expect_err("an extreme created must be refused, not accepted");
+            let msg = err.to_string();
+            assert!(
+                msg.contains("past") || msg.contains("future"),
+                "created={created} must be refused by a named direction, got: {msg}"
+            );
+        }
+    }
+
+    #[test]
+    fn created_301s_in_past_rejected() {
+        let err = sig_created_at_offset(-301).check_created().unwrap_err();
+        assert!(err.to_string().contains("past"), "{err}");
+    }
+
+    #[test]
+    fn created_299s_in_past_accepted() {
+        assert!(sig_created_at_offset(-299).check_created().is_ok());
+    }
+
+    #[test]
+    fn created_61s_in_future_rejected() {
+        let err = sig_created_at_offset(61).check_created().unwrap_err();
+        assert!(err.to_string().contains("future"), "{err}");
+    }
+
+    #[test]
+    fn created_30s_in_future_accepted() {
+        assert!(sig_created_at_offset(30).check_created().is_ok());
+    }
+
+    #[test]
+    fn created_exactly_now_accepted() {
+        assert!(sig_created_at_offset(0).check_created().is_ok());
+    }
+
     #[test]
     fn fresh_signature_passes_clock_skew() {
         let kp = Keypair::generate();

crates/gitlawb-node/src/metrics.rs

@@ -13,6 +13,9 @@
 //!     `gitlawb_webhook_deliveries_total{result}`
 //!   * is inbound gossip being admitted or shed, and for which reason?
 //!     `gitlawb_gossip_ingest_events_total{outcome}`
+//!   * is the gossip replay seen-set full, and therefore admitting events it
+//!     cannot deduplicate?
+//!     `gitlawb_gossip_replay_guard_saturated_total`
 //!   * how big are the packs we're sending and receiving? —
 //!     `gitlawb_pack_size_bytes`
 //!   * a single `gitlawb_info{version, did}` gauge = 1, for joins/dashboards
@@ -35,8 +38,8 @@
 use std::sync::OnceLock;
 
 use prometheus::{
-    Encoder, Histogram, HistogramOpts, IntCounterVec, IntGauge, IntGaugeVec, Opts, Registry,
-    TextEncoder,
+    Encoder, Histogram, HistogramOpts, IntCounter, IntCounterVec, IntGauge, IntGaugeVec, Opts,
+    Registry, TextEncoder,
 };
 
 /// The single, process-wide metrics registry. Initialized by [`init`].
@@ -52,6 +55,7 @@ static AUTH_FAILURES: OnceLock<IntCounterVec> = OnceLock::new();
 static SYNC_PROCESSED: OnceLock<IntCounterVec> = OnceLock::new();
 static WEBHOOK_DELIVERIES: OnceLock<IntCounterVec> = OnceLock::new();
 static GOSSIP_INGEST: OnceLock<IntCounterVec> = OnceLock::new();
+static GOSSIP_REPLAY_GUARD_SATURATED: OnceLock<IntCounter> = OnceLock::new();
 static PACK_SIZE: OnceLock<Histogram> = OnceLock::new();
 static PEERS_CONNECTED: OnceLock<IntGauge> = OnceLock::new();
 
@@ -186,6 +190,18 @@ fn init_inner(version: &str, node_did: &str) {
         .set(gossip_ingest)
         .expect("set GOSSIP_INGEST once");
 
+    let gossip_replay_guard_saturated = IntCounter::with_opts(Opts::new(
+        "gitlawb_gossip_replay_guard_saturated_total",
+        "Inbound gossip ref-updates admitted without being recorded because the replay seen-set was at capacity",
+    ))
+    .expect("gitlawb_gossip_replay_guard_saturated_total definition");
+    registry
+        .register(Box::new(gossip_replay_guard_saturated.clone()))
+        .expect("register gitlawb_gossip_replay_guard_saturated_total");
+    GOSSIP_REPLAY_GUARD_SATURATED
+        .set(gossip_replay_guard_saturated)
+        .expect("set GOSSIP_REPLAY_GUARD_SATURATED once");
+
     let pack_size = Histogram::with_opts(
         HistogramOpts::new(
             "gitlawb_pack_size_bytes",
@@ -290,7 +306,8 @@ pub fn record_webhook_delivery(result: &str) {
 
 /// Record what the gossip ingest path decided about one inbound ref-update.
 /// `outcome` ∈ {accepted, unsigned_admitted, write_failed, rejected,
-/// source_rate_limited, author_rate_limited, unsigned_source_rate_limited}.
+/// source_rate_limited, author_rate_limited, unsigned_source_rate_limited,
+/// replayed, stale_timestamp}.
 ///
 /// `accepted` is reserved for signature-verified events. An unsigned event that
 /// survives the rolling-upgrade window is `unsigned_admitted`, so the
@@ -315,6 +332,38 @@ pub fn record_gossip_ingest(outcome: &str) {
     }
 }
 
+/// Record one inbound gossip ref-update that the replay seen-set could not
+/// record because it was at capacity.
+///
+/// Label-less on purpose: there is one degradation mode and nothing about it
+/// varies per event, so a label would only add cardinality.
+///
+/// This is an alert-worthy signal, not a debug counter, and it is the ONLY way
+/// the degraded state is visible. At capacity the guard fails open, which means
+/// the event is admitted and `gitlawb_gossip_ingest_events_total{outcome=
+/// "accepted"}` counts it exactly as it counts a healthy admission. Fail-open is
+/// the right policy (a saturated set that dropped all fresh gossip would convert
+/// a loud resource attack into quiet mesh-wide censorship), but it is not a free
+/// one: while this counter is moving, a captured signature can again be replayed
+/// against the freshness window's full 10 minutes, spending a `peer_exists`
+/// round trip and a debit from the victim author's budget on every replay.
+pub fn record_gossip_replay_guard_saturated() {
+    if let Some(c) = GOSSIP_REPLAY_GUARD_SATURATED.get() {
+        c.inc();
+    }
+}
+
+/// Test-only: current `gitlawb_gossip_replay_guard_saturated_total` value (0 if
+/// the registry is not initialized). Lets the seen-set tests assert the
+/// saturation signal fires without scraping the encoded text.
+#[cfg(test)]
+pub fn replay_guard_saturated_count_for_test() -> u64 {
+    GOSSIP_REPLAY_GUARD_SATURATED
+        .get()
+        .map(|c| c.get())
+        .unwrap_or(0)
+}
+
 /// Record a pack body size observation (bytes).
 pub fn observe_pack_size(bytes: f64) {
     if let Some(h) = PACK_SIZE.get() {
@@ -410,6 +459,11 @@ mod tests {
         record_auth_failure("test/route", "test_reason");
         record_sync_processed("done");
         record_webhook_delivery("ok");
+        // `record_gossip_replay_guard_saturated` is deliberately NOT called
+        // here. It is a label-less process-wide counter and the seen-set test
+        // that asserts it asserts a before/after delta, so an increment from a
+        // second test running concurrently in this binary would be a flake with
+        // no diagnostic value.
         record_gossip_ingest("accepted");
         observe_pack_size(1024.0);
         set_peers_connected(0);