diff --git a/libs/langgraph/langgraph/pregel/_loop.py b/libs/langgraph/langgraph/pregel/_loop.py
index 09739420f..1633eba67 100644
--- a/libs/langgraph/langgraph/pregel/_loop.py
+++ b/libs/langgraph/langgraph/pregel/_loop.py
@@ -257,6 +257,8 @@ class PregelLoop:
     _resume_loaded_writes: Sequence[PendingWrite] = ()
     # Tasks `_reapply_writes_to_succeeded_nodes` handed loaded writes back to.
     _reapplied_task_ids: set[str]
+    # Tasks that wrote during this run, the only ones exit mode saves at exit.
+    _written_task_ids: set[str]
     # An update or fork checkpoint addressed by `checkpoint_id` that the thread
     # has moved past, so it may already have children.
     _addressed_checkpoint_superseded: bool = False
@@ -455,6 +457,7 @@ class PregelLoop:
         """Put writes for a task, to be read by the next tick."""
         if not writes:
             return
+        self._written_task_ids.add(task_id)
         # deduplicate writes to special channels, last write wins
         if all(w[0] in WRITES_IDX_MAP for w in writes):
             writes = list({w[0]: w for w in writes}.values())
@@ -561,10 +564,12 @@ class PregelLoop:
                 CONFIG_KEY_CHECKPOINT_ID: self.checkpoint["id"],
             },
         )
-        # group by task id
+        # Writes loaded with the checkpoint are stored on it already. Saving them
+        # again can file them under new indexes, and then they apply twice.
         by_task = defaultdict(list)
         for task_id, channel, value in self.checkpoint_pending_writes:
-            by_task[task_id].append((channel, value))
+            if task_id in self._written_task_ids:
+                by_task[task_id].append((channel, value))
         # submit writes to checkpointer
         for task_id, writes in by_task.items():
             if self.checkpointer_put_writes_accepts_task_path and hasattr(
@@ -909,6 +914,7 @@ class PregelLoop:
             if tid != NULL_TASK_ID and isinstance(self.specs.get(ch), DeltaChannel)
         }
         self._exit_command_writes = []
+        self._written_task_ids = set()
         # Resuming from a previous checkpoint requires two things:
         # 1. A prior checkpoint exists (channel_versions is non-empty)
         # 2. The input signals continuation (not a fresh run with new input)
diff --git a/libs/langgraph/tests/test_interrupt_state.py b/libs/langgraph/tests/test_interrupt_state.py
index e6c913dcf..a0a4832ef 100644
--- a/libs/langgraph/tests/test_interrupt_state.py
+++ b/libs/langgraph/tests/test_interrupt_state.py
@@ -152,6 +152,28 @@ def test_finished_task_does_not_report_answered_interrupt(
         assert asked == [["A1", "B"]]
 
 
+def test_finished_task_output_applies_once(
+    sync_checkpointer: BaseCheckpointSaver, durability: Durability
+) -> None:
+    builder = StateGraph(State)
+    builder.add_node("a", lambda s: {"log": [f"a:{interrupt('A')}"]})
+    builder.add_node("b", lambda s: {"log": [f"b:{interrupt('B')}"]})
+    builder.add_node("c", lambda s: {"log": [f"c:{interrupt('C')}"]})
+    builder.add_edge(START, "a")
+    builder.add_edge(START, "b")
+    builder.add_edge(START, "c")
+    graph = builder.compile(checkpointer=sync_checkpointer)
+    config = _config()
+
+    result = graph.invoke({"log": []}, config, durability=durability)
+    while pending := result.get("__interrupt__"):
+        result = graph.invoke(
+            Command(resume={pending[0].id: "yes"}), config, durability=durability
+        )
+
+    assert sorted(result["log"]) == ["a:yes", "b:yes", "c:yes"]
+
+
 def test_resume_with_update_applies_the_update_once(
     sync_checkpointer: BaseCheckpointSaver, durability: Durability
 ) -> None: