mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-08-08 20:30:59 +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>
369 lines
12 KiB
Python
369 lines
12 KiB
Python
"""
|
|
Unit tests for N8nServiceAPIRunner._process_response
|
|
|
|
Tests cover four scenarios:
|
|
- Stream adapter + n8n stream format (type:item/end)
|
|
- Stream adapter + n8n plain JSON
|
|
- Non-stream adapter + n8n stream format
|
|
- Non-stream adapter + n8n plain JSON
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import sys
|
|
from unittest.mock import AsyncMock, MagicMock, Mock, patch
|
|
|
|
import pytest
|
|
import langbot_plugin.api.entities.builtin.provider.message as provider_message
|
|
|
|
# Break the circular import chain while importing n8nsvapi:
|
|
# n8nsvapi → runner → app → pipelinemgr → all runners → runner (partially init)
|
|
# The stubs are restored in a ``finally`` block so this module does NOT pollute
|
|
# sys.modules for other test modules (e.g. ones importing the real
|
|
# LocalAgentRunner, which would otherwise inherit ``object`` and break).
|
|
# Mirrors master's intent but uses try/finally so a raised import doesn't
|
|
# leave the global namespace in a stubbed state, and includes
|
|
# ``langbot.pkg.utils.httpclient`` which master didn't stub.
|
|
_runner_stub = MagicMock()
|
|
_runner_stub.runner_class = lambda name: (lambda cls: cls) # no-op decorator
|
|
_runner_stub.RequestRunner = object
|
|
_import_stubs = {
|
|
'langbot.pkg.provider.runner': _runner_stub,
|
|
'langbot.pkg.core.app': MagicMock(),
|
|
'langbot.pkg.utils.httpclient': MagicMock(),
|
|
}
|
|
_saved_modules = {name: sys.modules.get(name) for name in _import_stubs}
|
|
for _name, _stub in _import_stubs.items():
|
|
sys.modules[_name] = _stub
|
|
try:
|
|
from langbot.pkg.provider.runners.n8nsvapi import (
|
|
N8nAPIError,
|
|
N8nServiceAPIRunner,
|
|
_MAX_N8N_RESPONSE_CHARS,
|
|
)
|
|
finally:
|
|
for _name, _original in _saved_modules.items():
|
|
if _original is None:
|
|
sys.modules.pop(_name, None)
|
|
else:
|
|
sys.modules[_name] = _original
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Helpers
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def make_runner(output_key: str = 'response') -> N8nServiceAPIRunner:
|
|
ap = Mock()
|
|
ap.logger = Mock()
|
|
pipeline_config = {
|
|
'ai': {
|
|
'n8n-service-api': {
|
|
'webhook-url': 'http://test-n8n/webhook',
|
|
'output-key': output_key,
|
|
'auth-type': 'none',
|
|
}
|
|
}
|
|
}
|
|
return N8nServiceAPIRunner(ap, pipeline_config)
|
|
|
|
|
|
def make_mock_response(chunks: list[bytes | str], status: int = 200):
|
|
"""Build a minimal aiohttp.ClientResponse mock with iter_chunked support."""
|
|
response = Mock()
|
|
response.status = status
|
|
|
|
async def iter_chunked(size):
|
|
for chunk in chunks:
|
|
yield chunk
|
|
|
|
response.content = Mock()
|
|
response.content.iter_chunked = iter_chunked
|
|
return response
|
|
|
|
|
|
async def collect_chunks(runner: N8nServiceAPIRunner, chunks: list[bytes | str]):
|
|
"""Run _process_response and collect all yielded MessageChunks."""
|
|
response = make_mock_response(chunks)
|
|
result = []
|
|
async for chunk in runner._process_response(response):
|
|
result.append(chunk)
|
|
return result
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# _process_response: stream format (type:item/end)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stream_format_single_item():
|
|
"""Single item + end in one chunk yields final chunk with full content."""
|
|
runner = make_runner()
|
|
data = b'{"type":"item","content":"hello"}{"type":"end"}'
|
|
|
|
chunks = await collect_chunks(runner, [data])
|
|
|
|
assert len(chunks) == 1
|
|
assert chunks[0].is_final is True
|
|
assert chunks[0].content == 'hello'
|
|
assert chunks[0].msg_sequence == 1
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stream_format_multi_item_accumulates():
|
|
"""Multiple items accumulate into full_content."""
|
|
runner = make_runner()
|
|
chunks_data = [
|
|
b'{"type":"item","content":"foo"}',
|
|
b'{"type":"item","content":"bar"}',
|
|
b'{"type":"end"}',
|
|
]
|
|
|
|
chunks = await collect_chunks(runner, chunks_data)
|
|
|
|
assert len(chunks) == 1
|
|
assert chunks[0].is_final is True
|
|
assert chunks[0].content == 'foobar'
|
|
assert chunks[0].msg_sequence == 1
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stream_format_batches_every_8_items():
|
|
"""Every 8th item triggers an intermediate yield before the final."""
|
|
runner = make_runner()
|
|
items = [f'{{"type":"item","content":"{i}"}}' for i in range(8)]
|
|
items.append('{"type":"end"}')
|
|
data = ''.join(items).encode()
|
|
|
|
chunks = await collect_chunks(runner, [data])
|
|
|
|
assert len(chunks) == 2
|
|
assert chunks[0].is_final is False
|
|
assert chunks[0].content == '01234567'
|
|
assert chunks[0].msg_sequence == 1
|
|
assert chunks[1].is_final is True
|
|
assert chunks[1].content == '01234567'
|
|
assert chunks[1].msg_sequence == 2
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stream_format_split_across_network_chunks():
|
|
"""JSON split across multiple network chunks is reassembled correctly."""
|
|
runner = make_runner()
|
|
part1 = b'{"type":"item","con'
|
|
part2 = b'tent":"world"}{"type":"end"}'
|
|
|
|
chunks = await collect_chunks(runner, [part1, part2])
|
|
|
|
assert len(chunks) == 1
|
|
assert chunks[0].is_final is True
|
|
assert chunks[0].content == 'world'
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stream_format_no_spurious_empty_yield():
|
|
"""chunk_idx==0 guard prevents spurious empty yield before any item is received."""
|
|
runner = make_runner()
|
|
# Send some non-stream JSON first, then stream
|
|
data = b'{"type":"item","content":"x"}{"type":"end"}'
|
|
|
|
chunks = await collect_chunks(runner, [data])
|
|
|
|
assert len(chunks) == 1
|
|
assert chunks[0].content == 'x'
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# _process_response: plain JSON fallback
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_plain_json_with_output_key():
|
|
"""Plain JSON with matching output_key extracts value via output_key."""
|
|
runner = make_runner(output_key='response')
|
|
data = json.dumps({'response': 'hello world'}).encode()
|
|
|
|
chunks = await collect_chunks(runner, [data])
|
|
|
|
assert len(chunks) == 1
|
|
assert chunks[0].is_final is True
|
|
assert chunks[0].content == 'hello world'
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_plain_json_output_key_not_found():
|
|
"""Plain JSON without output_key falls back to entire JSON string."""
|
|
runner = make_runner(output_key='response')
|
|
payload = {'other_key': 'hello'}
|
|
data = json.dumps(payload).encode()
|
|
|
|
chunks = await collect_chunks(runner, [data])
|
|
|
|
assert len(chunks) == 1
|
|
assert chunks[0].is_final is True
|
|
assert json.loads(chunks[0].content) == payload
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_plain_json_output_key_empty_string():
|
|
"""output_key present but value is empty string — returns empty string, not whole JSON."""
|
|
runner = make_runner(output_key='response')
|
|
data = json.dumps({'response': ''}).encode()
|
|
|
|
chunks = await collect_chunks(runner, [data])
|
|
|
|
assert len(chunks) == 1
|
|
assert chunks[0].is_final is True
|
|
assert chunks[0].content == ''
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_plain_json_non_dict_response():
|
|
"""Plain JSON array falls back to raw text."""
|
|
runner = make_runner()
|
|
data = b'["a", "b"]'
|
|
|
|
chunks = await collect_chunks(runner, [data])
|
|
|
|
assert len(chunks) == 1
|
|
assert chunks[0].is_final is True
|
|
assert chunks[0].content == '["a", "b"]'
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_response_size_is_bounded():
|
|
runner = make_runner()
|
|
|
|
with pytest.raises(N8nAPIError, match='exceeds the runtime limit'):
|
|
await collect_chunks(
|
|
runner,
|
|
[b'x' * (_MAX_N8N_RESPONSE_CHARS + 1)],
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_invalid_json_returns_raw_text():
|
|
"""Non-JSON response returns raw text as-is."""
|
|
runner = make_runner()
|
|
data = b'plain text response'
|
|
|
|
chunks = await collect_chunks(runner, [data])
|
|
|
|
assert len(chunks) == 1
|
|
assert chunks[0].is_final is True
|
|
assert chunks[0].content == 'plain text response'
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# _call_webhook: output type depends on is_stream
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def make_query(is_stream: bool):
|
|
"""Build a minimal Query mock."""
|
|
query = Mock()
|
|
query.adapter = AsyncMock()
|
|
query.adapter.is_stream_output_supported = AsyncMock(return_value=is_stream)
|
|
|
|
session = Mock()
|
|
session.using_conversation = Mock()
|
|
session.using_conversation.uuid = 'test-uuid'
|
|
session.launcher_type = Mock()
|
|
session.launcher_type.value = 'person'
|
|
session.launcher_id = '12345'
|
|
query.session = session
|
|
|
|
query.user_message = Mock()
|
|
query.user_message.content = 'hi'
|
|
query.variables = {}
|
|
return query
|
|
|
|
|
|
def make_http_session_mock(response_bytes: bytes, status: int = 200):
|
|
"""Mock httpclient.get_session() returning a session whose post() yields response_bytes."""
|
|
mock_response = make_mock_response([response_bytes], status=status)
|
|
mock_response.status = status
|
|
|
|
mock_cm = AsyncMock()
|
|
mock_cm.__aenter__ = AsyncMock(return_value=mock_response)
|
|
mock_cm.__aexit__ = AsyncMock(return_value=False)
|
|
|
|
mock_session = Mock()
|
|
mock_session.post = Mock(return_value=mock_cm)
|
|
return mock_session
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_call_webhook_nonstream_adapter_plain_json():
|
|
"""Non-stream adapter + plain JSON → single Message with output_key value."""
|
|
runner = make_runner(output_key='response')
|
|
query = make_query(is_stream=False)
|
|
http_session = make_http_session_mock(json.dumps({'response': 'result text'}).encode())
|
|
|
|
with patch('langbot.pkg.provider.runners.n8nsvapi.httpclient.get_session', return_value=http_session):
|
|
results = []
|
|
async for msg in runner._call_webhook(query):
|
|
results.append(msg)
|
|
|
|
assert len(results) == 1
|
|
assert isinstance(results[0], provider_message.Message)
|
|
assert results[0].content == 'result text'
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_call_webhook_stream_adapter_stream_format():
|
|
"""Stream adapter + stream format → MessageChunks, last is_final."""
|
|
runner = make_runner()
|
|
query = make_query(is_stream=True)
|
|
data = b'{"type":"item","content":"hi"}{"type":"end"}'
|
|
http_session = make_http_session_mock(data)
|
|
|
|
with patch('langbot.pkg.provider.runners.n8nsvapi.httpclient.get_session', return_value=http_session):
|
|
results = []
|
|
async for msg in runner._call_webhook(query):
|
|
results.append(msg)
|
|
|
|
assert all(isinstance(r, provider_message.MessageChunk) for r in results)
|
|
assert results[-1].is_final is True
|
|
assert results[-1].content == 'hi'
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_call_webhook_stream_adapter_plain_json():
|
|
"""Stream adapter + plain JSON → single MessageChunk with is_final=True."""
|
|
runner = make_runner(output_key='response')
|
|
query = make_query(is_stream=True)
|
|
data = json.dumps({'response': 'fallback'}).encode()
|
|
http_session = make_http_session_mock(data)
|
|
|
|
with patch('langbot.pkg.provider.runners.n8nsvapi.httpclient.get_session', return_value=http_session):
|
|
results = []
|
|
async for msg in runner._call_webhook(query):
|
|
results.append(msg)
|
|
|
|
assert all(isinstance(r, provider_message.MessageChunk) for r in results)
|
|
assert results[-1].is_final is True
|
|
assert results[-1].content == 'fallback'
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_call_webhook_nonstream_adapter_stream_format():
|
|
"""Non-stream adapter + stream format → single Message with accumulated content."""
|
|
runner = make_runner()
|
|
query = make_query(is_stream=False)
|
|
data = b'{"type":"item","content":"foo"}{"type":"item","content":"bar"}{"type":"end"}'
|
|
http_session = make_http_session_mock(data)
|
|
|
|
with patch('langbot.pkg.provider.runners.n8nsvapi.httpclient.get_session', return_value=http_session):
|
|
results = []
|
|
async for msg in runner._call_webhook(query):
|
|
results.append(msg)
|
|
|
|
assert len(results) == 1
|
|
assert isinstance(results[0], provider_message.Message)
|
|
assert results[0].content == 'foobar'
|