fix(langgraph): don't propagate ReplayState to subgraphs on plain resume (#7561)

**Description:**
When clients resume an interrupted subgraph with `Command(resume=...)`
plus an explicit `checkpoint_id` in the config (the pattern LangGraph
Studio and the API server emit on every resume), the subgraph restarts
from its first node instead of continuing at the interrupted node.

Fix: gate `ReplayState` propagation on `is_time_traveling` rather than
`is_replaying`, so a resume that happens to carry a head checkpoint_id
behaves the same as one with just a thread_id.

**Verification:** added regression test
`test_subgraph_interrupt_resume_with_explicit_head_checkpoint_id` (fails
on main, passes with fix, across memory/sqlite/sqlite_aes).
Full `test_time_travel.py`, `test_time_travel_async.py`,
`test_interruption.py`, and all pregel subgraph/interrupt/resume/replay
tests still pass.

Co-authored-by: Jessie Ibarra <jessie.ibarra@langgraph.dev>
This commit is contained in:
Jessie Ibarra
2026-04-20 21:29:18 -04:00
committed by GitHub
co-authored by Jessie Ibarra
parent b674dd4622
commit 0a26b471d3
2 changed files with 77 additions and 1 deletions
+11 -1
View File
@@ -831,8 +831,18 @@ class PregelLoop:
# parent. For forks (source=update/fork), use the fork's parent
# checkpoint ID since the fork was created after the subgraph's
# checkpoints from the original execution.
#
# Only gate on is_time_traveling (not is_replaying). When the
# client resumes with an explicit checkpoint_id that happens to
# point at the current head (e.g. LangGraph Studio sending
# `checkpoint: {checkpoint_id}` alongside Command(resume=...)),
# is_replaying is True but is_time_traveling is False. In that
# case subgraphs should load their latest checkpoint normally,
# not go through ReplayState's before-bound lookup which would
# miss subgraph checkpoints created during processing of the
# current parent step.
replay_state: ReplayState | None = None
if self.is_replaying:
if is_time_traveling:
replay_checkpoint_id = self.checkpoint["id"]
if (
self.checkpoint_metadata.get("source")
+66
View File
@@ -1113,6 +1113,72 @@ def test_subgraph_interrupt_replay_from_parent_then_resume(
]
def test_subgraph_interrupt_resume_with_explicit_head_checkpoint_id(
sync_checkpointer: BaseCheckpointSaver,
) -> None:
"""Resume with Command(resume=...) plus the current head checkpoint_id
in config. The subgraph must continue from the interrupted node, not
restart from scratch. Explicit checkpoint_id triggers is_replaying but
this is a resume, not a time-travel, so ReplayState should not apply."""
called: list[str] = []
def step_a(state: State) -> State:
called.append("step_a")
return {"value": ["sub_a"]}
def ask_human(state: State) -> State:
called.append("ask_human")
answer = interrupt("Provide input:")
return {"value": [f"human:{answer}"]}
def step_b(state: State) -> State:
called.append("step_b")
return {"value": ["sub_b"]}
subgraph = (
StateGraph(State)
.add_node("step_a", step_a)
.add_node("ask_human", ask_human)
.add_node("step_b", step_b)
.add_edge(START, "step_a")
.add_edge("step_a", "ask_human")
.add_edge("ask_human", "step_b")
.compile(checkpointer=True)
)
graph = (
StateGraph(State)
.add_node("subgraph_node", subgraph)
.add_edge(START, "subgraph_node")
.compile(checkpointer=sync_checkpointer)
)
config = {"configurable": {"thread_id": "1"}}
# Run until interrupt fires in subgraph
graph.invoke({"value": []}, config)
assert called == ["step_a", "ask_human"]
# Resume with explicit head checkpoint_id in config
head_checkpoint_id = graph.get_state(config).config["configurable"][
"checkpoint_id"
]
called.clear()
resume_config = {
"configurable": {
"thread_id": "1",
"checkpoint_id": head_checkpoint_id,
"checkpoint_ns": "",
}
}
result = graph.invoke(Command(resume="answer"), resume_config)
assert called == ["ask_human", "step_b"]
assert "__interrupt__" not in result
assert result["value"] == ["sub_a", "human:answer", "sub_b"]
def test_subgraph_replay_loads_accumulated_state_then_resume(
sync_checkpointer: BaseCheckpointSaver,
) -> None: