fix(node): keep attestation tasks alive after submission retry timeout

crates/node/src/metrics.rs

@@ -477,5 +477,17 @@ pub static MPC_TEE_ATTESTATION_ATTEMPTS_TOTAL: LazyLock<prometheus::IntCounterVe
         .unwrap()
     });
 
+/// A node that cannot get its attestation onto the contract retries forever rather than giving
+/// up, so this counter is the only signal an operator has that the node is failing to attest.
+pub static MPC_TEE_ATTESTATION_SUBMISSIONS_TOTAL: LazyLock<prometheus::IntCounterVec> =
+    LazyLock::new(|| {
+        prometheus::register_int_counter_vec!(
+            "mpc_tee_attestation_submissions_total",
+            "Total number of TEE attestation submissions to the MPC contract",
+            &["outcome"],
+        )
+        .unwrap()
+    });
+
 pub const MPC_TEE_ATTESTATION_OUTCOME_SUCCESS: &str = "success";
 pub const MPC_TEE_ATTESTATION_OUTCOME_FAILURE: &str = "failure";

crates/node/src/run.rs

@@ -358,33 +358,6 @@ where
         }),
     };
 
-    // Spawn periodic attestation submission task
-    let submitter = AttestationSubmitter {
-        tee_authority: tee_authority.clone(),
-        tx_sender: indexer_api.txn_sender.clone(),
-        tls_public_key: tls_public_key.clone(),
-        account_public_key: account_public_key.clone(),
-        allowed_image_hashes: indexer_api.allowed_docker_images_receiver.clone(),
-        allowed_launcher_compose_hashes: indexer_api.allowed_launcher_compose_receiver.clone(),
-        attestation_reader: indexer_api.attestation_reader.clone(),
-    };
-    tokio::spawn(async move {
-        if let Err(e) = periodic_attestation_submission(
-            submitter,
-            tokio::time::interval(ATTESTATION_RESUBMISSION_INTERVAL),
-        )
-        .await
-        {
-            tracing::error!(
-                error = ?e,
-                "periodic attestation submission task failed"
-            );
-        }
-    });
-
-    // Spawn TEE attestation monitoring task
-    let tee_accounts_receiver = indexer_api.attested_nodes_receiver.clone();
-    let account_id_clone = config.my_near_account_id.clone();
     let submitter = AttestationSubmitter {
         tee_authority,
         tx_sender: indexer_api.txn_sender.clone(),
@@ -394,16 +367,19 @@ where
         allowed_launcher_compose_hashes: indexer_api.allowed_launcher_compose_receiver.clone(),
         attestation_reader: indexer_api.attestation_reader.clone(),
     };
-    tokio::spawn(async move {
-        if let Err(e) =
-            monitor_attestation_removal(submitter, account_id_clone, tee_accounts_receiver).await
-        {
-            tracing::error!(
-                error = ?e,
-                "attestation removal monitoring task failed"
-            );
-        }
-    });
+    let mut attestation_interval = tokio::time::interval(ATTESTATION_RESUBMISSION_INTERVAL);
+    // A failed submission can retry internally for longer than the interval; skip the missed
+    // ticks instead of bursting stale submissions afterwards
+    attestation_interval.set_missed_tick_behavior(tokio::time::MissedTickBehavior::Skip);
+    tokio::spawn(periodic_attestation_submission(
+        submitter.clone(),
+        attestation_interval,
+    ));
+    tokio::spawn(monitor_attestation_removal(
+        submitter,
+        config.my_near_account_id.clone(),
+        indexer_api.attested_nodes_receiver.clone(),
+    ));
 
     let keyshare_storage: Arc<RwLock<KeyshareStorage>> =
         RwLock::new(key_storage_config.create().await?).into();