Special value to indicate that graph should interrupt on all nodes.
How the stream method should emit outputs.
"values": Emit all values in the state after each step, including interrupts.
When used with functional API, values are emitted once at the end of the workflow."updates": Emit only the node or task names and updates returned by the nodes or tasks after each step.
If multiple updates are made in the same step (e.g. multiple nodes are run) then those updates are emitted separately."custom": Emit custom data using from inside nodes or tasks using StreamWriter."messages": Emit LLM messages token-by-token together with metadata for any LLM invocations inside nodes or tasks."checkpoints": Emit an event when a checkpoint is created, in the same format as returned by get_state()."tasks": Emit events when tasks start and finish, including their results and errors."debug": Emit "checkpoints" and "tasks" events for debugging purposes.Merge multiple configs into one.
Raised when a subgraph is interrupted, suppressed by the root graph. Never raised directly, or surfaced to the user.
One or more commands to update the graph's state and send messages to nodes.
Typed container returned by invoke() / ainvoke() with version="v2".
Information about an interrupt that occurred in a node.
interrupt_id was introduced as a propertyThe following attributes have been removed:
nswhenresumableinterrupt_id, deprecated in favor of idA Pregel task.
Snapshot of the state of the graph at the beginning of a step.
Exception raised when an error occurs in the remote graph.
The RemoteGraph class is a client implementation for calling remote
APIs that implement the LangGraph Server API specification.
For example, the RemoteGraph class can be used to call APIs from deployments
on LangSmith Deployment.
RemoteGraph behaves the same way as a Graph and can be used directly as
a node in another Graph.
A discriminated union of all v2 stream part types.
Use part["type"] to narrow the type:
async for part in graph.astream(input, version="v2"):
if part["type"] == "values":
part["data"] # OutputT — full state (pydantic/dataclass/dict)
elif part["type"] == "messages":
part["data"] # tuple[BaseMessage, dict] — (message, metadata)
elif part["type"] == "custom":
part["data"] # Any — user-defined