Files
langgraph/libs/sdk-py/tests/integration/test_remote_graph_v3.py
Nick HollonandGitHub 68fa011fc9 feat(langgraph): add v3 streaming support to RemoteGraph (#7927)
## Summary

- Adds `stream_events(version="v3")` and `astream_events(version="v3")`
to `RemoteGraph`, matching the local `CompiledStateGraph` surface and
unblocking polymorphic v3 streaming over `Graph | RemoteGraph`.
- Implementation is a thin adapter
(`libs/langgraph/langgraph/pregel/_remote_run_stream.py`) that wraps the
v3 SDK's `AsyncThreadStream` / `SyncThreadStream` and duck-types
`GraphRunStream` / `AsyncGraphRunStream`. No coupling to local v3 mux
internals.
- `v1` / `v2` paths unchanged. `astream_events(version='v1'|'v2')` still
raises `NotImplementedError` (separate gap).

### Scope decisions baked into this PR

- Unsupported v3 kwargs hard-reject at dispatch with
`NotImplementedError`: `control`, `transformers`, `interrupt_before`,
`interrupt_after`, and any unknown `**kwargs`. Server / SDK don't plumb
these through v3 yet; easy to lift later.
- Sync `interleave()` raises `NotImplementedError` pointing callers at
`astream_events`. Real sync interleave would need drainer threads;
deferred since most sync RemoteGraph callers just iterate raw events.
- Async `interleave()` is best-effort ordering (client receive order),
documented as a divergence from local v3's monotonic stamp ordering.
- Adapter `interrupted` / `interrupts` properties are **non-blocking**
snapshots of the SDK's current state. This differs from local
`(Async)GraphRunStream.interrupted`, which pump-drives the run to
terminal before returning. Callers needing a wait-for-interrupt pattern
should drain a projection (e.g., `interleave('values')`) until the SDK's
paused sentinel fires. Documented in the adapter docstrings.

### Audit of impact

Existing RemoteGraph callers in this org all use the v2 `.stream()` /
`.astream()` path (deepagents production wrapper, langgraph-api test
graphs, langgraph-supervisor TS type guard). **Zero callers** use
`stream_events` / `astream_events` on RemoteGraph today, so the new v3
methods are net-new surface — no risk of breaking existing consumers.

### Out of scope (follow-ups)

- Bumping `libs/langgraph/pyproject.toml`'s `langgraph-sdk` constraint
from `<0.4.0` to `<0.5.0`. Deferred until 0.4.0 publishes to PyPI; dev
resolution unaffected via the editable workspace dep.
- Real `astream_events(version='v1'|'v2')` implementation.
- Server-side plumbing for `control` / `interrupt_before` /
`interrupt_after` on v3 runs.
- Sync `interleave()` via drainer threads.


## Test plan

- [x] \`make test\` in \`libs/langgraph/\`: 1874 passed, 4 skipped (43
new in \`test_remote_graph_v3.py\`)
- [x] \`make lint\` in \`libs/langgraph/\`: ruff + mypy clean
- [x] \`pytest -m integration
tests/integration/test_remote_graph_v3.py\` in \`libs/sdk-py/\` against
the docker stack: 4/4 passed in 1.35s
- [x] Manual smoke: \`RemoteGraph('tools_agent',
url='http://localhost:2024').astream_events(..., version='v3')\`
end-to-end against the v3 integration api
- [x] Existing RemoteGraph v2 tests untouched (31 passed, 3 skipped with
docker up)
- [x] Will need rebase after \`langgraph-sdk 0.4.0\` lands on PyPI and
the version constraint is bumped in a separate PR
2026-05-29 17:13:43 -04:00

134 lines
4.8 KiB
Python

"""Integration tests for RemoteGraph v3 streaming.
Tests the end-to-end wiring: RemoteGraph -> langgraph_sdk client.threads.stream(...) ->
docker-running langgraph-api -> SSE projections -> adapter classes.
Run with: pytest tests/integration/test_remote_graph_v3.py -m integration
"""
from __future__ import annotations
import uuid
import pytest
from langchain_core.runnables import RunnableConfig
from langgraph.pregel.remote import RemoteGraph
from langgraph.types import Command
pytestmark = pytest.mark.integration
URL = "http://localhost:2024"
# Input shapes matching what the integration graphs expect.
# `agent` graph (streaming_graph.py): AgentState has messages, value, items.
# `tools_agent` graph (tools_agent.py): create_agent graph expects messages list.
_AGENT_INPUT = {"messages": [], "value": "init", "items": []}
_TOOLS_AGENT_INPUT = {"messages": [{"role": "user", "content": "search for v3"}]}
@pytest.fixture
def remote_agent() -> RemoteGraph:
return RemoteGraph("agent", url=URL)
@pytest.fixture
def remote_tools_agent() -> RemoteGraph:
return RemoteGraph("tools_agent", url=URL)
async def test_async_happy_path_yields_output(remote_tools_agent: RemoteGraph) -> None:
"""tools_agent completes without interrupt; ``await stream.output`` drives
the run to terminal via the lifecycle watcher (no explicit event iteration
needed — the SSE subscription stays open by design after run completion)."""
async with await remote_tools_agent.astream_events(
_TOOLS_AGENT_INPUT,
version="v3",
) as stream:
output = await stream.output()
assert output is not None
assert (await stream.interrupted()) is False
async def test_async_interrupt_path_surfaces_interrupts(
remote_agent: RemoteGraph,
) -> None:
"""agent graph hits ask_human; interrupted must be True with >= 1 interrupt.
Note: interrupts pause the run but DON'T resolve `_run_done` (only
`completed` / `failed` lifecycle phases do), so `await stream.output()`
would hang. The adapter doesn't expose `interleave()` on the async
side (mirrors local `AsyncGraphRunStream`), so drain the `values`
projection directly until the run reports it is interrupted.
"""
async with await remote_agent.astream_events(
_AGENT_INPUT,
version="v3",
) as stream:
async for _ in stream.values:
if await stream.interrupted():
break
assert (await stream.interrupted()) is True
interrupts = await stream.interrupts()
assert len(interrupts) >= 1
async def test_async_resume_after_interrupt(remote_agent: RemoteGraph) -> None:
"""Interrupt the agent at ask_human, then resume the SAME thread with
`Command(resume=...)`.
Validates the v3 resume path end-to-end. The client sends the raw resume
value as `input` (not a serialized Command); the server detects the
thread's pending interrupt from persisted state — which survives the first
session's close — and wraps it as `Command(resume=...)`, driving the run
past `ask_human` to completion (the graph interrupts only once).
"""
thread_id = str(uuid.uuid4())
config: RunnableConfig = {"configurable": {"thread_id": thread_id}}
# First session: drive until the agent pauses at the ask_human interrupt.
async with await remote_agent.astream_events(
_AGENT_INPUT,
config=config,
version="v3",
) as stream:
async for _ in stream.values:
if await stream.interrupted():
break
assert (await stream.interrupted()) is True
# Second session on the same thread: resume with the human's answer. The
# run continues past ask_human to completion with no further interrupt.
async with await remote_agent.astream_events(
Command(resume="yes"),
config=config,
version="v3",
) as stream:
output = await stream.output()
assert output is not None
assert (await stream.interrupted()) is False
def test_sync_happy_path_yields_output(remote_tools_agent: RemoteGraph) -> None:
"""Sync stream: tools_agent completes; ``stream.output`` (sync property)
blocks until terminal."""
with remote_tools_agent.stream_events(
_TOOLS_AGENT_INPUT,
version="v3",
) as stream:
output = stream.output
assert output is not None
assert stream.interrupted is False
async def test_abort_mid_run_cancels_server_side(
remote_tools_agent: RemoteGraph,
) -> None:
"""Abort immediately after run.start; reaching the end without exception
confirms abort + __aexit__ cleanup worked."""
async with await remote_tools_agent.astream_events(
_TOOLS_AGENT_INPUT,
version="v3",
) as stream:
await stream.abort()
# Reaching here without unhandled exceptions confirms abort + __aexit__ succeeded.