mirror of
https://github.com/langchain-ai/langgraph.git
synced 2026-10-20 06:51:41 +02:00
## Summary
Thread streams in `langgraph_sdk` now report why they ended. An `id:
null` error frame becomes the error `thread.output` raises, the sync
client no longer blocks forever when the server closes the stream, and a
stream the server rejects with a 4xx ends at once instead of being
retried.
## Problem
- A server sends `{"type": "error", "id": null, ...}` just before it
closes a thread stream whose read failed. The SDK dropped the frame, so
`thread.output` raised a generic "lifecycle stream ended before terminal
event" (async) or blocked forever (sync: the lifecycle watcher returned
without settling the run).
- A 403 or 404 on the stream request was retried like a network error,
then reported as `RuntimeError("Lifecycle transport failed: ...")` with
no status. A server that rejects a WebSocket after accepting it closes
with 4000 plus the HTTP status (4403, 4404, 4422), since a browser can't
read a refused upgrade's status. The shared stream counted each such
reconnect as a success and reconnected forever.
## Fix
- The lifecycle watcher fails the run with the frame's error on a clean
close (both clients). The shared stream logs the frame instead of
dropping it: projections still end when the stream closes, as before,
and `thread.output` carries the error.
- A 4xx other than 408 and 429, as a status or as a 4000+status close
code, ends the stream without retries. `thread.output` now raises that
`httpx.HTTPStatusError` or `websockets.exceptions.ConnectionClosedError`
instead of the generic `RuntimeError`.
- For a minted `thread_id`, the lifecycle watcher starts after
`run.start` creates the thread. Without this, the 4xx stop would turn a
stream opened under custom auth for a not-yet-created thread from
retried into failed. The sync client starts it under a lock, since
`run.start` can be called from several threads.
- Drops the first of two `SyncStreamController._reconnect_shared_stream`
definitions. It was shadowed by the second and never ran.
Not in this PR: over WebSocket the server closes with 1011 after an
error frame, which is still retried, while over SSE the close is clean
and fails the stream. Reconnecting after a clean close, as
`langchain-ai/langgraphjs#2812` does for the JS SDK, is a separate
change.
## Test plan
- [x] The 10 new behavior tests (async and sync: error frame, clean
close, 404, 4404 close, reconnect on 404, minted `thread_id`) fail on
`main` and pass here; a race test checks that two concurrent `run.start`
calls start one watcher.
- [x] `make test` in `libs/sdk-py`: 541 passed. `make lint` clean,
`check_sdk_methods.py` passes.
- [x] `RemoteGraph` v3 tests in `libs/langgraph`
(`test_remote_graph_v3.py`,
`test_stream_events_v3_kwarg_forwarding.py`): 94 passed against this
SDK.
- [x] Against a local server with custom auth: a thread the caller can't
read fails at once with 404 (SSE) or 4404 (WebSocket), and a new thread
works with a 1 s pause before `run.start`, which fails on `main`.
133 lines
5.0 KiB
Python
133 lines
5.0 KiB
Python
"""Synchronous fake v3 protocol server for sync streaming tests."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from collections.abc import Iterator
|
|
from dataclasses import dataclass
|
|
from typing import Any
|
|
|
|
import httpx
|
|
import orjson
|
|
|
|
|
|
@dataclass
|
|
class SyncStreamScript:
|
|
events: list[dict[str, Any]]
|
|
fail_after: int | None = None
|
|
status: int = 200
|
|
|
|
|
|
class _SseByteStream(httpx.SyncByteStream):
|
|
def __init__(self, script: SyncStreamScript) -> None:
|
|
self._script = script
|
|
|
|
def __iter__(self) -> Iterator[bytes]:
|
|
for index, event in enumerate(self._script.events, start=1):
|
|
payload = orjson.dumps(event).decode()
|
|
yield f"id: {event.get('event_id', '')}\n".encode()
|
|
yield f"event: message\ndata: {payload}\n\n".encode()
|
|
if self._script.fail_after is not None and index >= self._script.fail_after:
|
|
raise httpx.ReadError("scripted sync stream failure")
|
|
|
|
|
|
class SyncFakeServer:
|
|
"""Synchronous fake for `/commands`, `/stream/events`, and `/state`."""
|
|
|
|
def __init__(self) -> None:
|
|
self.received_commands: list[dict[str, Any]] = []
|
|
self.stream_request_bodies: list[dict[str, Any]] = []
|
|
self.command_request_headers: list[dict[str, str]] = []
|
|
self.stream_request_headers_list: list[dict[str, str]] = []
|
|
self.state_request_headers: list[dict[str, str]] = []
|
|
self.state_request_count = 0
|
|
self.scripted_events: list[dict[str, Any]] = []
|
|
self.state: dict[str, Any] = {}
|
|
self.transport = httpx.MockTransport(self._handle)
|
|
self._stream_scripts: list[SyncStreamScript] = []
|
|
self._command_response: dict[str, Any] | None = None
|
|
self.graph_response: dict[str, Any] = {
|
|
"nodes": [{"id": "agent", "type": "runnable", "data": {"name": "agent"}}],
|
|
"edges": [],
|
|
}
|
|
self.graph_request_params: list[dict[str, str]] = []
|
|
self.graph_request_headers: list[dict[str, str]] = []
|
|
|
|
def script(
|
|
self,
|
|
events: list[dict[str, Any]],
|
|
*,
|
|
fail_after: int | None = None,
|
|
) -> None:
|
|
self.scripted_events = list(events)
|
|
self._stream_scripts = [
|
|
SyncStreamScript(events=list(events), fail_after=fail_after)
|
|
]
|
|
|
|
def script_sequence(self, scripts: list[SyncStreamScript]) -> None:
|
|
self._stream_scripts = list(scripts)
|
|
self.scripted_events = []
|
|
|
|
def set_graph(self, graph: dict[str, Any]) -> None:
|
|
self.graph_response = dict(graph)
|
|
|
|
def script_command_response(self, response: dict[str, Any]) -> None:
|
|
self._command_response = dict(response)
|
|
|
|
def set_state(
|
|
self,
|
|
values: dict[str, Any],
|
|
next: list[Any] | None = None,
|
|
metadata: dict[str, Any] | None = None,
|
|
) -> None:
|
|
self.state = {
|
|
"values": values,
|
|
"next": next if next is not None else [],
|
|
"tasks": [],
|
|
"metadata": metadata if metadata is not None else {},
|
|
"checkpoint": None,
|
|
"created_at": None,
|
|
}
|
|
|
|
def _handle(self, request: httpx.Request) -> httpx.Response:
|
|
path = request.url.path
|
|
if path.endswith("/commands"):
|
|
body = orjson.loads(request.content)
|
|
self.received_commands.append(body)
|
|
self.command_request_headers.append(dict(request.headers))
|
|
if self._command_response is not None:
|
|
response = dict(self._command_response)
|
|
response["id"] = body.get("id")
|
|
return httpx.Response(200, json=response)
|
|
return httpx.Response(
|
|
200,
|
|
json={
|
|
"type": "success",
|
|
"id": body.get("id"),
|
|
"result": {"run_id": "run-1"},
|
|
},
|
|
)
|
|
if path.endswith("/stream/events"):
|
|
self.stream_request_bodies.append(orjson.loads(request.content))
|
|
self.stream_request_headers_list.append(dict(request.headers))
|
|
script = (
|
|
self._stream_scripts.pop(0)
|
|
if self._stream_scripts
|
|
else SyncStreamScript(events=list(self.scripted_events))
|
|
)
|
|
if script.status != 200:
|
|
return httpx.Response(script.status, json={"detail": "scripted"})
|
|
return httpx.Response(
|
|
200,
|
|
headers={"content-type": "text/event-stream"},
|
|
stream=_SseByteStream(script),
|
|
)
|
|
if path.endswith("/graph") and "/assistants/" in path:
|
|
self.graph_request_params.append(dict(request.url.params))
|
|
self.graph_request_headers.append(dict(request.headers))
|
|
return httpx.Response(200, json=self.graph_response)
|
|
if path.endswith("/state"):
|
|
self.state_request_count += 1
|
|
self.state_request_headers.append(dict(request.headers))
|
|
return httpx.Response(200, json=self.state)
|
|
return httpx.Response(404, json={"error": f"unexpected path: {path}"})
|