Streaming and human approval

Stream modes

Mode	Payload	Typical use
`values`	Complete state after each commit	UI state mirrors, debugging
`updates`	Node/superstep state deltas	Lightweight progress
`events`	Lifecycle events with sequence and metadata	Tracing, audit, Studio
`custom`	Raw values from `stream_writer(value)`	Tokens, business progress
`messages`	`(AIMessageChunk/AIMessage, metadata)`	Chat token streams

async for mode, chunk in graph.astream(
    input_state,
    context={"tenant": "acme"},
    stream_mode=["updates", "custom", "messages"],
):
    print(mode, chunk)

Custom output wakes the consumer immediately; it does not wait for the node to finish or the superstep to commit:

def retrieve(state, runtime):
    runtime.stream_writer({"stage": "searching"})
    docs = search(state["query"])
    runtime.stream_writer({"stage": "found", "count": len(docs)})
    return {"documents": docs}

Streaming is an observation channel and does not participate in reducers. Closing the iterator cancels unfinished tasks and propagates the cancellation token.

Dynamic interrupts

from lingxigraph import interrupt


def approve(state):
    decision = interrupt({
        "kind": "approval",
        "action": state["proposed_action"],
    })
    return {"approved": bool(decision["approved"])}

The graph needs a checkpointer and stable thread_id. At interrupt(), it saves a checkpoint and pauses. On resume, the node replays from its beginning, so side effects before the interrupt must also be idempotent.

from lingxigraph import Command

config = {"configurable": {"thread_id": "ticket-42"}}
graph.invoke(initial, config=config)
graph.invoke(Command(resume={"approved": True}), config=config)

In Agent Server, the original run becomes paused. Resume creates a new run pinned to the same graph/version/config/context:

curl -X POST http://localhost:8124/v1/runs/$RUN_ID/resume \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"resume":{"approved":true}}'

Show reviewers only the fields they need. Never put secrets, tokens, or complete sensitive state in interrupts, events, or traces.

Get started

Core concepts

Guides

API reference

Operations and project

Streaming and human approval

Stream modes

Dynamic interrupts

​Stream modes

​Dynamic interrupts

Stream modes

Dynamic interrupts