mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-08-09 12:40:59 +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
@@ -2,15 +2,17 @@
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import contextlib
|
||||
import json
|
||||
import typing
|
||||
import httpx
|
||||
import sqlalchemy
|
||||
|
||||
from ..core import app as core_app
|
||||
from ..core import entities as core_entities
|
||||
from ..entity.persistence.metadata import Metadata
|
||||
from ..utils import constants
|
||||
from ..persistence.tenant_uow import CrossScopeTransactionError
|
||||
from ..utils import constants, httpclient
|
||||
|
||||
SURVEY_TRIGGERED_KEY = 'survey_triggered_events'
|
||||
BOT_RESPONSE_COUNT_KEY = 'survey_bot_response_count'
|
||||
@@ -36,15 +38,41 @@ class SurveyManager:
|
||||
await self._load_triggered_events()
|
||||
await self._load_bot_response_count()
|
||||
|
||||
@contextlib.asynccontextmanager
|
||||
async def _instance_transaction(self):
|
||||
"""Bind instance-global survey metadata to an explicit Cloud transaction."""
|
||||
|
||||
persistence_mgr = self.ap.persistence_mgr
|
||||
try:
|
||||
active_session = getattr(persistence_mgr, 'current_session', lambda: None)()
|
||||
except CrossScopeTransactionError:
|
||||
# A newly-created child task inherited its parent's ContextVar;
|
||||
# opening an explicit UoW below gives it an independent session.
|
||||
active_session = None
|
||||
if active_session is not None:
|
||||
yield
|
||||
return
|
||||
|
||||
cloud_runtime = getattr(getattr(persistence_mgr, 'mode', None), 'value', None) == 'cloud_runtime'
|
||||
if cloud_runtime:
|
||||
instance_uow = getattr(persistence_mgr, 'instance_discovery_uow', None)
|
||||
if not callable(instance_uow):
|
||||
raise RuntimeError('Cloud survey metadata requires an explicit instance UoW')
|
||||
async with instance_uow(self.ap.workspace_service.instance_uuid):
|
||||
yield
|
||||
return
|
||||
yield
|
||||
|
||||
async def _load_triggered_events(self):
|
||||
"""Load previously triggered events from metadata table."""
|
||||
try:
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.select(Metadata).where(Metadata.key == SURVEY_TRIGGERED_KEY)
|
||||
)
|
||||
row = result.first()
|
||||
if row:
|
||||
self._triggered_events = set(json.loads(row[0].value))
|
||||
async with self._instance_transaction():
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.select(Metadata.value).where(Metadata.key == SURVEY_TRIGGERED_KEY)
|
||||
)
|
||||
value = result.scalar_one_or_none()
|
||||
if value is not None:
|
||||
self._triggered_events = set(json.loads(value))
|
||||
except Exception:
|
||||
self._triggered_events = set()
|
||||
|
||||
@@ -52,17 +80,18 @@ class SurveyManager:
|
||||
"""Persist triggered events to metadata table."""
|
||||
try:
|
||||
value = json.dumps(list(self._triggered_events))
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.select(Metadata).where(Metadata.key == SURVEY_TRIGGERED_KEY)
|
||||
)
|
||||
if result.first():
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.update(Metadata).where(Metadata.key == SURVEY_TRIGGERED_KEY).values(value=value)
|
||||
)
|
||||
else:
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.insert(Metadata).values(key=SURVEY_TRIGGERED_KEY, value=value)
|
||||
async with self._instance_transaction():
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.select(Metadata.value).where(Metadata.key == SURVEY_TRIGGERED_KEY)
|
||||
)
|
||||
if result.scalar_one_or_none() is not None:
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.update(Metadata).where(Metadata.key == SURVEY_TRIGGERED_KEY).values(value=value)
|
||||
)
|
||||
else:
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.insert(Metadata).values(key=SURVEY_TRIGGERED_KEY, value=value)
|
||||
)
|
||||
except Exception as e:
|
||||
self.ap.logger.debug(f'Failed to save survey triggered events: {e}')
|
||||
|
||||
@@ -75,12 +104,13 @@ class SurveyManager:
|
||||
async def _load_bot_response_count(self):
|
||||
"""Load the persisted successful bot response count from metadata table."""
|
||||
try:
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.select(Metadata).where(Metadata.key == BOT_RESPONSE_COUNT_KEY)
|
||||
)
|
||||
row = result.first()
|
||||
if row:
|
||||
self._bot_response_count = int(row[0].value)
|
||||
async with self._instance_transaction():
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.select(Metadata.value).where(Metadata.key == BOT_RESPONSE_COUNT_KEY)
|
||||
)
|
||||
value = result.scalar_one_or_none()
|
||||
if value is not None:
|
||||
self._bot_response_count = int(value)
|
||||
except Exception:
|
||||
self._bot_response_count = 0
|
||||
|
||||
@@ -88,17 +118,18 @@ class SurveyManager:
|
||||
"""Persist the successful bot response count to metadata table."""
|
||||
try:
|
||||
value = str(self._bot_response_count)
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.select(Metadata).where(Metadata.key == BOT_RESPONSE_COUNT_KEY)
|
||||
)
|
||||
if result.first():
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.update(Metadata).where(Metadata.key == BOT_RESPONSE_COUNT_KEY).values(value=value)
|
||||
)
|
||||
else:
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.insert(Metadata).values(key=BOT_RESPONSE_COUNT_KEY, value=value)
|
||||
async with self._instance_transaction():
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.select(Metadata.value).where(Metadata.key == BOT_RESPONSE_COUNT_KEY)
|
||||
)
|
||||
if result.scalar_one_or_none() is not None:
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.update(Metadata).where(Metadata.key == BOT_RESPONSE_COUNT_KEY).values(value=value)
|
||||
)
|
||||
else:
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
sqlalchemy.insert(Metadata).values(key=BOT_RESPONSE_COUNT_KEY, value=value)
|
||||
)
|
||||
except Exception as e:
|
||||
self.ap.logger.debug(f'Failed to save survey bot response count: {e}')
|
||||
|
||||
@@ -131,7 +162,13 @@ class SurveyManager:
|
||||
await self._save_triggered_events()
|
||||
|
||||
# Check for pending survey asynchronously
|
||||
asyncio.create_task(self._fetch_pending_survey(event))
|
||||
self.ap.task_mgr.create_task(
|
||||
self._fetch_pending_survey(event),
|
||||
kind='survey-fetch',
|
||||
name=f'survey-fetch-{event}',
|
||||
scopes=[core_entities.LifecycleControlScope.APPLICATION],
|
||||
instance_uuid=self.ap.workspace_service.instance_uuid,
|
||||
)
|
||||
|
||||
async def _fetch_pending_survey(self, event: str):
|
||||
"""Fetch pending survey from Space for this event."""
|
||||
@@ -141,10 +178,13 @@ class SurveyManager:
|
||||
'instance_id': constants.instance_id,
|
||||
'event': event,
|
||||
}
|
||||
async with httpx.AsyncClient(timeout=httpx.Timeout(10)) as client:
|
||||
async with httpx.AsyncClient(
|
||||
timeout=httpx.Timeout(10),
|
||||
event_hooks=httpclient.httpx_response_limit_hooks(),
|
||||
) as client:
|
||||
resp = await client.post(url, json=payload)
|
||||
if resp.status_code == 200:
|
||||
data = resp.json()
|
||||
data = await httpclient.parse_json_response(resp)
|
||||
if data.get('code') == 0 and data.get('data', {}).get('survey'):
|
||||
self._pending_survey = data['data']['survey']
|
||||
self.ap.logger.info(f'Survey pending: {self._pending_survey.get("survey_id")}')
|
||||
@@ -187,7 +227,10 @@ class SurveyManager:
|
||||
'metadata': await self._build_base_metadata(),
|
||||
'completed': completed,
|
||||
}
|
||||
async with httpx.AsyncClient(timeout=httpx.Timeout(10)) as client:
|
||||
async with httpx.AsyncClient(
|
||||
timeout=httpx.Timeout(10),
|
||||
event_hooks=httpclient.httpx_response_limit_hooks(),
|
||||
) as client:
|
||||
resp = await client.post(url, json=payload)
|
||||
if resp.status_code == 200:
|
||||
self.clear_pending_survey()
|
||||
@@ -214,11 +257,15 @@ class SurveyManager:
|
||||
'attachments': attachments,
|
||||
'metadata': metadata,
|
||||
}
|
||||
async with httpx.AsyncClient(timeout=httpx.Timeout(30)) as client:
|
||||
async with httpx.AsyncClient(
|
||||
timeout=httpx.Timeout(30),
|
||||
event_hooks=httpclient.httpx_response_limit_hooks(),
|
||||
) as client:
|
||||
resp = await client.post(url, json=payload)
|
||||
if resp.status_code == 200:
|
||||
return True
|
||||
self.ap.logger.warning(f'Failed to submit feedback: {resp.status_code} {resp.text[:200]}')
|
||||
body = await httpclient.response_text(resp, max_chars=200)
|
||||
self.ap.logger.warning(f'Failed to submit feedback: {resp.status_code} {body}')
|
||||
except Exception as e:
|
||||
self.ap.logger.warning(f'Failed to submit feedback: {e}')
|
||||
return False
|
||||
@@ -233,7 +280,10 @@ class SurveyManager:
|
||||
'survey_id': survey_id,
|
||||
'instance_id': constants.instance_id,
|
||||
}
|
||||
async with httpx.AsyncClient(timeout=httpx.Timeout(10)) as client:
|
||||
async with httpx.AsyncClient(
|
||||
timeout=httpx.Timeout(10),
|
||||
event_hooks=httpclient.httpx_response_limit_hooks(),
|
||||
) as client:
|
||||
resp = await client.post(url, json=payload)
|
||||
if resp.status_code == 200:
|
||||
self.clear_pending_survey()
|
||||
|
||||
Reference in New Issue
Block a user