mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-08-09 04:40:57 +00:00
feat(tenancy): add Workspace multi-tenant foundation (#2353)
* 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>
This commit is contained in:
RockChinQ
@@ -6,6 +6,56 @@ import json
|
||||
|
||||
from .errors import WeKnoraAPIError
|
||||
|
||||
_MAX_WENKORA_RESPONSE_BYTES = 1024 * 1024
|
||||
_MAX_WENKORA_STREAM_BYTES = 16 * 1024 * 1024
|
||||
_MAX_WENKORA_SSE_LINE_BYTES = 1024 * 1024
|
||||
|
||||
|
||||
async def _read_limited_response(response: httpx.Response) -> bytes:
|
||||
body = bytearray()
|
||||
async for chunk in response.aiter_bytes(chunk_size=8192):
|
||||
body.extend(chunk)
|
||||
if len(body) > _MAX_WENKORA_RESPONSE_BYTES:
|
||||
raise WeKnoraAPIError('WeKnora response exceeds the runtime limit')
|
||||
return bytes(body)
|
||||
|
||||
|
||||
async def _iter_sse_json(
|
||||
response: httpx.Response,
|
||||
) -> typing.AsyncGenerator[dict[str, typing.Any], None]:
|
||||
buffer = bytearray()
|
||||
total = 0
|
||||
async for chunk in response.aiter_bytes(chunk_size=8192):
|
||||
total += len(chunk)
|
||||
if total > _MAX_WENKORA_STREAM_BYTES:
|
||||
raise WeKnoraAPIError('WeKnora stream exceeds the runtime limit')
|
||||
buffer.extend(chunk)
|
||||
while b'\n' in buffer:
|
||||
raw_line, _, remainder = buffer.partition(b'\n')
|
||||
buffer = bytearray(remainder)
|
||||
if len(raw_line) > _MAX_WENKORA_SSE_LINE_BYTES:
|
||||
raise WeKnoraAPIError('WeKnora SSE event exceeds the runtime limit')
|
||||
line = raw_line.rstrip(b'\r').strip()
|
||||
if not line.startswith(b'data:'):
|
||||
continue
|
||||
try:
|
||||
data = json.loads(line[5:].strip())
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
if isinstance(data, dict):
|
||||
yield data
|
||||
if len(buffer) > _MAX_WENKORA_SSE_LINE_BYTES:
|
||||
raise WeKnoraAPIError('WeKnora SSE event exceeds the runtime limit')
|
||||
|
||||
line = bytes(buffer).rstrip(b'\r').strip()
|
||||
if line.startswith(b'data:'):
|
||||
try:
|
||||
data = json.loads(line[5:].strip())
|
||||
except json.JSONDecodeError:
|
||||
return
|
||||
if isinstance(data, dict):
|
||||
yield data
|
||||
|
||||
|
||||
class AsyncWeKnoraClient:
|
||||
"""WeKnora API 客户端"""
|
||||
@@ -39,19 +89,19 @@ class AsyncWeKnoraClient:
|
||||
if description:
|
||||
payload['description'] = description
|
||||
|
||||
response = await client.post(
|
||||
async with client.stream(
|
||||
'POST',
|
||||
'/sessions',
|
||||
headers={
|
||||
'X-API-Key': self.api_key,
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
json=payload,
|
||||
)
|
||||
|
||||
if response.status_code not in (200, 201):
|
||||
raise WeKnoraAPIError(f'{response.status_code} {response.text}')
|
||||
|
||||
data = response.json()
|
||||
) as response:
|
||||
body = await _read_limited_response(response)
|
||||
if response.status_code not in (200, 201):
|
||||
raise WeKnoraAPIError(f'{response.status_code} {body.decode("utf-8", errors="replace")}')
|
||||
data = json.loads(body)
|
||||
return data['data']['id']
|
||||
|
||||
async def agent_chat(
|
||||
@@ -107,20 +157,13 @@ class AsyncWeKnoraClient:
|
||||
},
|
||||
json=payload,
|
||||
) as r:
|
||||
async for chunk in r.aiter_lines():
|
||||
if r.status_code != 200:
|
||||
raise WeKnoraAPIError(f'{r.status_code} {chunk}')
|
||||
if chunk.strip() == '':
|
||||
continue
|
||||
if chunk.startswith('data:'):
|
||||
try:
|
||||
data = json.loads(chunk[5:].strip())
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
yield data
|
||||
# 收到 error 事件后主动结束流，避免上层未 raise 时持续等待
|
||||
if data.get('response_type') == 'error':
|
||||
return
|
||||
if r.status_code != 200:
|
||||
body = await _read_limited_response(r)
|
||||
raise WeKnoraAPIError(f'{r.status_code} {body.decode("utf-8", errors="replace")}')
|
||||
async for data in _iter_sse_json(r):
|
||||
yield data
|
||||
if data.get('response_type') == 'error':
|
||||
return
|
||||
|
||||
async def knowledge_chat(
|
||||
self,
|
||||
@@ -164,17 +207,10 @@ class AsyncWeKnoraClient:
|
||||
},
|
||||
json=payload,
|
||||
) as r:
|
||||
async for chunk in r.aiter_lines():
|
||||
if r.status_code != 200:
|
||||
raise WeKnoraAPIError(f'{r.status_code} {chunk}')
|
||||
if chunk.strip() == '':
|
||||
continue
|
||||
if chunk.startswith('data:'):
|
||||
try:
|
||||
data = json.loads(chunk[5:].strip())
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
yield data
|
||||
# 收到 error 事件后主动结束流，避免上层未 raise 时持续等待
|
||||
if data.get('response_type') == 'error':
|
||||
return
|
||||
if r.status_code != 200:
|
||||
body = await _read_limited_response(r)
|
||||
raise WeKnoraAPIError(f'{r.status_code} {body.decode("utf-8", errors="replace")}')
|
||||
async for data in _iter_sse_json(r):
|
||||
yield data
|
||||
if data.get('response_type') == 'error':
|
||||
return
|
||||
|
||||
Reference in New Issue
Block a user