From 93182f054564574abbdbd1ad391b76b036bfe298 Mon Sep 17 00:00:00 2001
From: erhant <erhany96@gmail.com>
Date: Thu, 9 Jul 2026 14:02:38 +0300
Subject: [PATCH] fix(indexer): do not park immediately on possibly-transient
 apply failures

---
 lez/indexer/core/src/block_store.rs  | 48 ++++++++++++++++++++++++++++
 lez/indexer/core/src/ingest_error.rs | 13 ++++++++
 lez/indexer/core/src/lib.rs          |  9 ++++++
 3 files changed, 70 insertions(+)

diff --git a/lez/indexer/core/src/block_store.rs b/lez/indexer/core/src/block_store.rs
index ed142285..db3bed79 100644
--- a/lez/indexer/core/src/block_store.rs
+++ b/lez/indexer/core/src/block_store.rs
@@ -29,6 +29,11 @@ pub enum AcceptOutcome {
     AlreadyApplied,
     /// Did not chain or failed to apply; tip stays frozen, stall recorded.
     Parked(BlockIngestError),
+    /// Chained but failed to apply, possibly transiently
+    /// ([`BlockIngestError::is_retryable`]); nothing recorded, tip and state
+    /// untouched. The caller retries and parks via
+    /// [`IndexerStore::record_stall`] once it gives up.
+    ApplyFailed(BlockIngestError),
 }
 
 #[derive(Clone)]
@@ -254,6 +259,9 @@ impl IndexerStore {
         // TODO: we use scratch state to be atomic, but need to revisit how expensive a clone is
         let mut scratch = self.current_state.read().await.clone();
         if let Err(err) = apply_block_to_scratch(block, &mut scratch) {
+            if err.is_retryable() {
+                return Ok(AcceptOutcome::ApplyFailed(err));
+            }
             self.record_stall(Some(&block.header), l1_slot, err.clone())?;
             return Ok(AcceptOutcome::Parked(err));
         }
@@ -876,4 +884,44 @@ mod accept_tests {
         let reopened = IndexerStore::open_db(dir.path()).expect("reopen");
         assert_eq!(reopened.last_block().unwrap(), Some(101));
     }
+
+    #[tokio::test]
+    async fn transient_apply_failure_returns_apply_failed_without_stall() {
+        use testnet_initial_state::initial_pub_accounts_private_keys;
+
+        let dir = tempfile::tempdir().expect("tempdir");
+        let store = IndexerStore::open_db(dir.path()).expect("open store");
+
+        let accounts = initial_pub_accounts_private_keys();
+        let from = accounts[0].account_id;
+        let to = accounts[1].account_id;
+        let sign_key = accounts[0].pub_sign_key.clone();
+
+        let genesis = produce_dummy_block(1, None, vec![]);
+        store
+            .accept_block(&genesis, Slot::from(0))
+            .await
+            .expect("accept genesis");
+
+        // Overdraft: rejected during execution → StateTransition → retryable.
+        let tx = common::test_utils::create_transaction_native_token_transfer(
+            from,
+            0,
+            to,
+            1_000_000_000,
+            &sign_key,
+        );
+        let block = produce_dummy_block(2, Some(genesis.header.hash), vec![tx]);
+        let outcome = store.accept_block(&block, Slot::from(0)).await.unwrap();
+
+        assert!(matches!(
+            outcome,
+            AcceptOutcome::ApplyFailed(BlockIngestError::StateTransition { .. })
+        ));
+        assert!(
+            store.get_stall_reason().unwrap().is_none(),
+            "retryable failure must not persist a stall"
+        );
+        assert_eq!(store.get_last_block_id().unwrap(), Some(1), "tip frozen");
+    }
 }
diff --git a/lez/indexer/core/src/ingest_error.rs b/lez/indexer/core/src/ingest_error.rs
index bda53497..299013d7 100644
--- a/lez/indexer/core/src/ingest_error.rs
+++ b/lez/indexer/core/src/ingest_error.rs
@@ -40,6 +40,19 @@ pub enum BlockIngestError {
     },
 }
 
+impl BlockIngestError {
+    /// Whether the failure may be transient rather than a property of the block.
+    ///
+    /// FIXME: `StateTransition` is too coarse — its `reason` string mixes genuine
+    /// state-transition rejections with infra failures (risc0 executor teardown,
+    /// storage errors). Once it carries a structured cause, narrow this so only
+    /// infra failures retry.
+    #[must_use]
+    pub const fn is_retryable(&self) -> bool {
+        matches!(self, Self::StateTransition { .. })
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
diff --git a/lez/indexer/core/src/lib.rs b/lez/indexer/core/src/lib.rs
index 77839296..f748bf75 100644
--- a/lez/indexer/core/src/lib.rs
+++ b/lez/indexer/core/src/lib.rs
@@ -236,6 +236,15 @@ impl IndexerCore {
                             // L1 proceeds regardless
                             self.advance_cursor(&mut cursor, slot);
                         }
+                        Ok(AcceptOutcome::ApplyFailed(ingest_err)) => {
+                            error!(
+                                "Apply failed at block {}: {ingest_err}",
+                                block.header.block_id
+                            );
+                            self.set_status(IndexerSyncStatus::error(ingest_err.to_string()));
+                            had_cycle_error = true;
+                            break;
+                        }
                         Err(err) => {
                             // Infrastructure error (DB read/write), not a bad block.
                             // will re-poll from the same cursor next cycle.