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
@@ -1,9 +1,12 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
|
||||
import boto3
|
||||
from botocore.exceptions import ClientError
|
||||
|
||||
from ...core import app
|
||||
from ...utils import bounded_executor
|
||||
from .. import provider
|
||||
|
||||
|
||||
@@ -14,6 +17,7 @@ class S3StorageProvider(provider.StorageProvider):
|
||||
super().__init__(ap)
|
||||
self.s3_client = None
|
||||
self.bucket_name = None
|
||||
self._io_semaphore = asyncio.Semaphore(16)
|
||||
|
||||
async def initialize(self):
|
||||
"""Initialize S3 client with configuration from config.yaml"""
|
||||
@@ -26,6 +30,11 @@ class S3StorageProvider(provider.StorageProvider):
|
||||
secret_access_key = s3_config.get('secret_access_key', '')
|
||||
region_name = s3_config.get('region', 'us-east-1')
|
||||
self.bucket_name = s3_config.get('bucket', 'langbot-storage')
|
||||
try:
|
||||
max_concurrency = int(s3_config.get('max_concurrency', 16))
|
||||
except (TypeError, ValueError):
|
||||
max_concurrency = 16
|
||||
self._io_semaphore = asyncio.Semaphore(max(1, min(max_concurrency, 128)))
|
||||
|
||||
# Initialize S3 client
|
||||
session = boto3.session.Session()
|
||||
@@ -37,7 +46,25 @@ class S3StorageProvider(provider.StorageProvider):
|
||||
aws_secret_access_key=secret_access_key,
|
||||
)
|
||||
|
||||
# Ensure bucket exists
|
||||
await self._run_io(self._ensure_bucket)
|
||||
|
||||
async def shutdown(self) -> None:
|
||||
"""Close the botocore HTTP connection pool without blocking the loop."""
|
||||
|
||||
client = self.s3_client
|
||||
self.s3_client = None
|
||||
if client is not None:
|
||||
await bounded_executor.run_blocking_cleanup(client.close)
|
||||
|
||||
async def _run_io(self, operation, /, *args, **kwargs):
|
||||
"""Run one blocking boto3 operation behind a bounded concurrency gate."""
|
||||
|
||||
async with self._io_semaphore:
|
||||
return await asyncio.to_thread(operation, *args, **kwargs)
|
||||
|
||||
def _ensure_bucket(self) -> None:
|
||||
"""Probe/create the bucket without blocking the application event loop."""
|
||||
|
||||
try:
|
||||
self.s3_client.head_bucket(Bucket=self.bucket_name)
|
||||
except ClientError as e:
|
||||
@@ -61,7 +88,8 @@ class S3StorageProvider(provider.StorageProvider):
|
||||
):
|
||||
"""Save bytes to S3"""
|
||||
try:
|
||||
self.s3_client.put_object(
|
||||
await self._run_io(
|
||||
self.s3_client.put_object,
|
||||
Bucket=self.bucket_name,
|
||||
Key=key,
|
||||
Body=value,
|
||||
@@ -73,25 +101,48 @@ class S3StorageProvider(provider.StorageProvider):
|
||||
async def load(
|
||||
self,
|
||||
key: str,
|
||||
) -> bytes:
|
||||
return await self.load_bounded(key, max_bytes=provider.HARD_MAX_STORAGE_OBJECT_BYTES)
|
||||
|
||||
async def load_bounded(
|
||||
self,
|
||||
key: str,
|
||||
*,
|
||||
max_bytes: int,
|
||||
) -> bytes:
|
||||
"""Load bytes from S3"""
|
||||
max_bytes = provider.normalize_read_limit(max_bytes)
|
||||
try:
|
||||
response = self.s3_client.get_object(
|
||||
Bucket=self.bucket_name,
|
||||
Key=key,
|
||||
)
|
||||
return response['Body'].read()
|
||||
return await self._run_io(self._load_sync, key, max_bytes)
|
||||
except Exception as e:
|
||||
self.ap.logger.error(f'Failed to load from S3: {e}')
|
||||
raise
|
||||
|
||||
def _load_sync(self, key: str, max_bytes: int) -> bytes:
|
||||
response = self.s3_client.get_object(
|
||||
Bucket=self.bucket_name,
|
||||
Key=key,
|
||||
)
|
||||
body = response['Body']
|
||||
try:
|
||||
declared_size = response.get('ContentLength')
|
||||
if declared_size is not None and declared_size > max_bytes:
|
||||
raise ValueError(f'Storage object exceeds the {max_bytes}-byte read limit')
|
||||
value = body.read(max_bytes + 1)
|
||||
if len(value) > max_bytes:
|
||||
raise ValueError(f'Storage object exceeds the {max_bytes}-byte read limit')
|
||||
return value
|
||||
finally:
|
||||
body.close()
|
||||
|
||||
async def exists(
|
||||
self,
|
||||
key: str,
|
||||
) -> bool:
|
||||
"""Check if object exists in S3"""
|
||||
try:
|
||||
self.s3_client.head_object(
|
||||
await self._run_io(
|
||||
self.s3_client.head_object,
|
||||
Bucket=self.bucket_name,
|
||||
Key=key,
|
||||
)
|
||||
@@ -109,7 +160,8 @@ class S3StorageProvider(provider.StorageProvider):
|
||||
):
|
||||
"""Delete object from S3"""
|
||||
try:
|
||||
self.s3_client.delete_object(
|
||||
await self._run_io(
|
||||
self.s3_client.delete_object,
|
||||
Bucket=self.bucket_name,
|
||||
Key=key,
|
||||
)
|
||||
@@ -123,7 +175,8 @@ class S3StorageProvider(provider.StorageProvider):
|
||||
) -> int:
|
||||
"""Get object size from S3 without downloading it"""
|
||||
try:
|
||||
response = self.s3_client.head_object(
|
||||
response = await self._run_io(
|
||||
self.s3_client.head_object,
|
||||
Bucket=self.bucket_name,
|
||||
Key=key,
|
||||
)
|
||||
@@ -138,23 +191,23 @@ class S3StorageProvider(provider.StorageProvider):
|
||||
):
|
||||
"""Delete all objects with the given prefix (directory)"""
|
||||
try:
|
||||
# Ensure dir_path ends with /
|
||||
if not dir_path.endswith('/'):
|
||||
dir_path = dir_path + '/'
|
||||
|
||||
# List all objects with the prefix
|
||||
paginator = self.s3_client.get_paginator('list_objects_v2')
|
||||
pages = paginator.paginate(Bucket=self.bucket_name, Prefix=dir_path)
|
||||
|
||||
# Delete all objects
|
||||
for page in pages:
|
||||
if 'Contents' in page:
|
||||
objects_to_delete = [{'Key': obj['Key']} for obj in page['Contents']]
|
||||
if objects_to_delete:
|
||||
self.s3_client.delete_objects(
|
||||
Bucket=self.bucket_name,
|
||||
Delete={'Objects': objects_to_delete},
|
||||
)
|
||||
await self._run_io(self._delete_dir_recursive_sync, dir_path)
|
||||
except Exception as e:
|
||||
self.ap.logger.error(f'Failed to delete directory from S3: {e}')
|
||||
raise
|
||||
|
||||
def _delete_dir_recursive_sync(self, dir_path: str) -> None:
|
||||
if not dir_path.endswith('/'):
|
||||
dir_path = dir_path + '/'
|
||||
|
||||
paginator = self.s3_client.get_paginator('list_objects_v2')
|
||||
pages = paginator.paginate(Bucket=self.bucket_name, Prefix=dir_path)
|
||||
for page in pages:
|
||||
if 'Contents' not in page:
|
||||
continue
|
||||
objects_to_delete = [{'Key': obj['Key']} for obj in page['Contents']]
|
||||
if objects_to_delete:
|
||||
self.s3_client.delete_objects(
|
||||
Bucket=self.bucket_name,
|
||||
Delete={'Objects': objects_to_delete},
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user