mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-08-09 20:50:58 +00:00
e1ac5e0fc8
* Document multi-tenant workspace architecture * Add OSS and commercial workspace boundaries * docs: redesign multi-tenant workspace architecture * feat(tenancy): implement workspace isolation * docs(tenancy): record verification evidence * docs(tenancy): revise single-instance SaaS topology * docs(tenancy): refine architecture options * docs: finalize cloud v2 multi-tenant decisions * feat(tenancy): establish cloud isolation foundations * feat(tenancy): harden shared cloud runtime boundaries * docs(tenancy): record final isolation verification * fix(tenancy): close isolation and permission gaps * docs(tenancy): record final isolation verification * feat(tenancy): connect cloud workspace control plane * fix(build): install git for pinned SDK * docs(cloud): update control plane verification * chore: update multi-tenant SDK pin * fix(cloud): skip legacy model sync during startup * test(cloud): preserve minimal model manager fixtures * fix(cloud): preserve authenticated account context * fix(cloud): reuse authenticated account for user info * feat(cloud): complete Workspace settings navigation * test(web): cover Workspace dropdown menu * feat(web): place workspace controls in sidebar * refactor(web): streamline workspace controls * style(web): format workspace layout test * fix(cloud): surface runtime and workspace plan status * fix(plugin): keep runtime identity stable across restarts * fix(ui): widen and center workspace switcher * fix(ui): hide roles from workspace switcher * fix(ui): align workspace switcher with sidebar entries * feat(workspace): add in-product collaboration and direct Cloud launch * style: format collaboration changes * fix(workspace): bind collaboration APIs to tenant UoW * fix(cloud): preserve Core-owned collaboration state * test(cloud): require Space identity for invite registration * feat(cloud): complete secure invitation experience * style(web): format invitation flows * fix(cloud): recover box runtime without unscoped skill reload * feat(oss): enforce invitation account and owner billing flows * style: format OSS account service * test(oss): cover invitation logout handoff * fix(oss): resolve workspace owner in scoped session * feat(cloud): harden multi-tenant runtime resources * fix(cloud): bound runtime restart storms * fix(cloud): eliminate periodic runtime CPU spikes * fix(cloud): enforce instance capacity ceilings * fix(cloud): scope public login capability discovery * fix(cloud): bound tenant maintenance and monitoring work * fix(runtime): bound tenant resource amplification * fix(deps): pin green multi-tenant plugin SDK * fix(cloud): handle unavailable skill capability * fix(security): require authentication for image file endpoint (H-2) - Changed /api/v1/files/image from AuthType.NONE to USER_TOKEN_OR_API_KEY - Added Permission.RESOURCE_VIEW requirement - Prevents unauthenticated cross-tenant file access via leaked keys - Fixes HIGH severity finding from multi-tenant security review docs: add comprehensive database migration guide - Complete migration steps for OSS → multi-tenant - Backup, execution, verification procedures - Rollback scenarios and recovery plans - Performance tuning recommendations * test: add comprehensive cross-tenant isolation tests Added 7 critical test scenarios for multi-tenant boundaries: - Cross-tenant bot access prevention - Viewer role read-only enforcement - Removed member immediate access revocation - Model provider credential isolation - WebSocket message isolation - Invitation token workspace scoping - Multi-workspace context validation These tests address P0-2 coverage gaps for: - workspaces.py (membership & invitation flows) - user.py (authentication & authorization) - websocket_chat.py (real-time isolation) - plugins.py (resource access control) docs: finalize database migration guide * fix(security): resolve M-1, M-2, M-3 security findings M-1: WebSocket authorization TOCTOU race (FIXED) - Changed _revalidate_websocket_authorization to return RequestContext - Ensures validated context is used immediately without race window - Prevents removed members from sending messages during revalidation gap M-2: Model Manager cache workspace isolation (VERIFIED) - Confirmed _CacheKey already uses 4-tuple: (instance, workspace, generation, resource) - Cache is properly scoped per workspace, no cross-tenant leakage possible - No code change needed, documented as working correctly M-3: Invitation lock workspace scoping (FIXED) - Changed lock key from token_digest to workspace_uuid:token_digest - Prevents DoS where attacker locks token in Workspace A to block Workspace B - Locks now isolated per workspace All MEDIUM severity findings from security review now resolved. * fix(cloud): unblock tenant CI and enforce knowledge quotas * fix(tenancy): scope rerank model sync --------- Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>
316 lines
12 KiB
Python
316 lines
12 KiB
Python
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import json
|
|
from contextlib import asynccontextmanager
|
|
from types import SimpleNamespace
|
|
from typing import Any, cast
|
|
from unittest.mock import AsyncMock, Mock
|
|
|
|
import httpx
|
|
import pytest
|
|
from aiohttp import web
|
|
from mcp import types as mcp_types
|
|
|
|
from langbot.pkg.api.http.context import ExecutionContext
|
|
from langbot.pkg.provider.tools.loaders.mcp import MCPToolCallTimeoutError, RuntimeMCPSession
|
|
|
|
|
|
TEST_EXECUTION_CONTEXT = ExecutionContext(
|
|
instance_uuid='instance-a',
|
|
workspace_uuid='workspace-a',
|
|
placement_generation=1,
|
|
)
|
|
|
|
|
|
class _TransportProbe:
|
|
def __init__(self, streamable_status: int | None) -> None:
|
|
self.streamable_status = streamable_status
|
|
self.streamable_posts = 0
|
|
self.streamable_messages: list[str] = []
|
|
self.sse_gets = 0
|
|
self.sse_messages: list[str] = []
|
|
self.streamable_request_started = asyncio.Event()
|
|
self.release_streamable_request = asyncio.Event()
|
|
self._sse_response: web.StreamResponse | None = None
|
|
|
|
async def handle_mcp_endpoint(self, request: web.Request) -> web.StreamResponse:
|
|
if request.method == 'POST':
|
|
self.streamable_posts += 1
|
|
self.streamable_request_started.set()
|
|
if self.streamable_status is None:
|
|
await self.release_streamable_request.wait()
|
|
return web.Response(status=204)
|
|
if self.streamable_status == 200:
|
|
message = await request.json()
|
|
method = message.get('method', '')
|
|
self.streamable_messages.append(method)
|
|
if method == 'initialize':
|
|
return web.json_response(
|
|
{
|
|
'jsonrpc': '2.0',
|
|
'id': message['id'],
|
|
'result': {
|
|
'protocolVersion': mcp_types.LATEST_PROTOCOL_VERSION,
|
|
'capabilities': {'tools': {}},
|
|
'serverInfo': {'name': 'streamable-test', 'version': '1.0.0'},
|
|
},
|
|
}
|
|
)
|
|
if method == 'tools/list':
|
|
return web.json_response(
|
|
{
|
|
'jsonrpc': '2.0',
|
|
'id': message['id'],
|
|
'result': {
|
|
'tools': [
|
|
{
|
|
'name': 'echo',
|
|
'description': 'Echo test input',
|
|
'inputSchema': {'type': 'object'},
|
|
}
|
|
]
|
|
},
|
|
}
|
|
)
|
|
if method == 'tools/call':
|
|
tool_name = message.get('params', {}).get('name')
|
|
if tool_name == 'hang':
|
|
return web.Response(status=202)
|
|
return web.json_response(
|
|
{
|
|
'jsonrpc': '2.0',
|
|
'id': message['id'],
|
|
'result': {
|
|
'content': [
|
|
{
|
|
'type': 'text',
|
|
'text': 'healthy',
|
|
}
|
|
],
|
|
'isError': False,
|
|
},
|
|
}
|
|
)
|
|
return web.Response(status=202)
|
|
return web.Response(status=self.streamable_status)
|
|
|
|
self.sse_gets += 1
|
|
response = web.StreamResponse(
|
|
status=200,
|
|
headers={
|
|
'Content-Type': 'text/event-stream',
|
|
'Cache-Control': 'no-cache',
|
|
},
|
|
)
|
|
await response.prepare(request)
|
|
self._sse_response = response
|
|
await response.write(b'event: endpoint\ndata: /messages?session_id=test-session\n\n')
|
|
try:
|
|
while request.transport is not None and not request.transport.is_closing():
|
|
await asyncio.sleep(0.05)
|
|
except asyncio.CancelledError:
|
|
raise
|
|
return response
|
|
|
|
async def handle_sse_message(self, request: web.Request) -> web.Response:
|
|
message = await request.json()
|
|
method = message.get('method', '')
|
|
self.sse_messages.append(method)
|
|
|
|
if method == 'initialize':
|
|
response_message = {
|
|
'jsonrpc': '2.0',
|
|
'id': message['id'],
|
|
'result': {
|
|
'protocolVersion': mcp_types.LATEST_PROTOCOL_VERSION,
|
|
'capabilities': {},
|
|
'serverInfo': {'name': 'legacy-sse-test', 'version': '1.0.0'},
|
|
},
|
|
}
|
|
assert self._sse_response is not None
|
|
payload = json.dumps(response_message, separators=(',', ':'))
|
|
await self._sse_response.write(f'event: message\ndata: {payload}\n\n'.encode())
|
|
|
|
return web.Response(status=202)
|
|
|
|
|
|
@asynccontextmanager
|
|
async def _transport_server(streamable_status: int | None):
|
|
probe = _TransportProbe(streamable_status)
|
|
application = web.Application()
|
|
application.router.add_route('*', '/mcp', probe.handle_mcp_endpoint)
|
|
application.router.add_post('/messages', probe.handle_sse_message)
|
|
runner = web.AppRunner(application, shutdown_timeout=0.1)
|
|
await runner.setup()
|
|
site = web.TCPSite(runner, '127.0.0.1', 0)
|
|
await site.start()
|
|
server = cast(asyncio.Server, site._server)
|
|
port = server.sockets[0].getsockname()[1]
|
|
try:
|
|
yield probe, f'http://127.0.0.1:{port}/mcp'
|
|
finally:
|
|
await runner.cleanup()
|
|
|
|
|
|
def _session(
|
|
url: str,
|
|
*,
|
|
timeout: float = 2,
|
|
tool_call_timeout_sec: float = 300,
|
|
) -> RuntimeMCPSession:
|
|
app = cast(
|
|
Any,
|
|
SimpleNamespace(
|
|
logger=Mock(),
|
|
workspace_service=SimpleNamespace(
|
|
get_execution_binding=AsyncMock(
|
|
return_value=SimpleNamespace(
|
|
instance_uuid=TEST_EXECUTION_CONTEXT.instance_uuid,
|
|
workspace_uuid=TEST_EXECUTION_CONTEXT.workspace_uuid,
|
|
placement_generation=TEST_EXECUTION_CONTEXT.placement_generation,
|
|
)
|
|
)
|
|
),
|
|
),
|
|
)
|
|
return RuntimeMCPSession(
|
|
'remote-transport-test',
|
|
{
|
|
'uuid': 'srv-1',
|
|
'mode': 'remote',
|
|
'url': url,
|
|
'timeout': timeout,
|
|
'tool_call_timeout_sec': tool_call_timeout_sec,
|
|
},
|
|
True,
|
|
app,
|
|
TEST_EXECUTION_CONTEXT,
|
|
)
|
|
|
|
|
|
def _contains_http_status(exc: BaseException, status_code: int) -> bool:
|
|
return any(
|
|
isinstance(leaf, httpx.HTTPStatusError) and leaf.response.status_code == status_code
|
|
for leaf in RuntimeMCPSession._iter_exception_leaves(exc)
|
|
)
|
|
|
|
|
|
async def _close_session(session: RuntimeMCPSession) -> None:
|
|
await session.exit_stack.aclose()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_remote_transport_real_streamable_http_success_keeps_session_usable():
|
|
async with _transport_server(200) as (probe, url):
|
|
session = _session(url)
|
|
try:
|
|
await session._init_remote_server()
|
|
assert session.session is not None
|
|
tools = await session.session.list_tools()
|
|
assert [tool.name for tool in tools.tools] == ['echo']
|
|
assert probe.streamable_posts >= 2
|
|
assert probe.streamable_messages[:2] == ['initialize', 'notifications/initialized']
|
|
assert 'tools/list' in probe.streamable_messages
|
|
assert probe.sse_gets == 0
|
|
finally:
|
|
await _close_session(session)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_remote_transport_tool_timeout_does_not_poison_session():
|
|
async with _transport_server(200) as (probe, url):
|
|
session = _session(url, tool_call_timeout_sec=0.05)
|
|
try:
|
|
await session._init_remote_server()
|
|
|
|
with pytest.raises(MCPToolCallTimeoutError, match='timed out after 0.05 seconds'):
|
|
await session.invoke_mcp_tool('hang', {})
|
|
|
|
result = await session.invoke_mcp_tool('health_check', {})
|
|
|
|
assert result[0].text == 'healthy'
|
|
assert probe.streamable_messages.count('tools/call') == 2
|
|
finally:
|
|
await _close_session(session)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize('status_code', [400, 404, 405])
|
|
async def test_remote_transport_real_streamable_http_error_falls_back_to_legacy_sse(status_code: int):
|
|
async with _transport_server(status_code) as (probe, url):
|
|
session = _session(url)
|
|
try:
|
|
await session._init_remote_server()
|
|
assert session.session is not None
|
|
assert probe.streamable_posts == 1
|
|
assert probe.sse_gets == 1
|
|
assert 'initialize' in probe.sse_messages
|
|
finally:
|
|
await _close_session(session)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize('status_code', [401, 403, 406, 415, 429, 500])
|
|
async def test_remote_transport_real_non_compatibility_error_does_not_fallback(status_code: int):
|
|
async with _transport_server(status_code) as (probe, url):
|
|
session = _session(url)
|
|
try:
|
|
with pytest.raises(BaseException) as exc_info:
|
|
await session._init_remote_server()
|
|
assert _contains_http_status(exc_info.value, status_code)
|
|
assert probe.streamable_posts == 1
|
|
assert probe.sse_gets == 0
|
|
finally:
|
|
await _close_session(session)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_remote_transport_real_timeout_does_not_fallback():
|
|
async with _transport_server(None) as (probe, url):
|
|
session = _session(url, timeout=0.05)
|
|
try:
|
|
with pytest.raises(BaseException) as exc_info:
|
|
await session._init_remote_server()
|
|
assert any(
|
|
isinstance(leaf, httpx.TimeoutException)
|
|
for leaf in RuntimeMCPSession._iter_exception_leaves(exc_info.value)
|
|
)
|
|
assert probe.streamable_posts == 1
|
|
assert probe.sse_gets == 0
|
|
finally:
|
|
probe.release_streamable_request.set()
|
|
await _close_session(session)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize('error_type', [httpx.ConnectError, httpx.ConnectTimeout])
|
|
async def test_remote_transport_connection_errors_do_not_fallback(error_type: type[httpx.RequestError]):
|
|
request = httpx.Request('POST', 'https://unreachable.invalid/mcp')
|
|
error = error_type('connection failed', request=request)
|
|
session = _session(str(request.url))
|
|
session._init_streamable_http_server = AsyncMock(side_effect=error)
|
|
session._init_sse_server = AsyncMock()
|
|
|
|
with pytest.raises(type(error)) as exc_info:
|
|
await session._init_remote_server()
|
|
|
|
assert exc_info.value is error
|
|
session._init_sse_server.assert_not_awaited()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_remote_transport_external_cancellation_is_not_converted_to_sse_fallback():
|
|
async with _transport_server(None) as (probe, url):
|
|
session = _session(url)
|
|
task = asyncio.create_task(session._init_remote_server())
|
|
await asyncio.wait_for(probe.streamable_request_started.wait(), timeout=2)
|
|
task.cancel()
|
|
try:
|
|
with pytest.raises(asyncio.CancelledError):
|
|
await task
|
|
assert probe.sse_gets == 0
|
|
finally:
|
|
probe.release_streamable_request.set()
|
|
await _close_session(session)
|