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
@@ -1,21 +1,167 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import sqlalchemy
|
||||
import sqlalchemy.ext.asyncio as sqlalchemy_asyncio
|
||||
|
||||
from .. import database
|
||||
from ..postgresql_url import normalize_asyncpg_url
|
||||
|
||||
|
||||
MAX_POOL_CONNECTIONS = 100
|
||||
MAX_POOL_TIMEOUT_SECONDS = 300
|
||||
MAX_POOL_RECYCLE_SECONDS = 86_400
|
||||
MAX_STATEMENT_TIMEOUT_MS = 300_000
|
||||
MAX_LOCK_TIMEOUT_MS = 60_000
|
||||
MAX_IDLE_TRANSACTION_TIMEOUT_MS = 300_000
|
||||
|
||||
|
||||
@database.manager_class('postgresql')
|
||||
class PostgreSQLDatabaseManager(database.BaseDatabaseManager):
|
||||
"""PostgreSQL database manager"""
|
||||
|
||||
async def initialize(self) -> None:
|
||||
postgresql_config = self.ap.instance_config.data.get('database', {}).get('postgresql', {})
|
||||
@staticmethod
|
||||
def _pool_integer(
|
||||
config: dict,
|
||||
name: str,
|
||||
default: int,
|
||||
*,
|
||||
minimum: int,
|
||||
maximum: int,
|
||||
) -> int:
|
||||
value = config.get(name, default)
|
||||
if isinstance(value, bool) or not isinstance(value, int) or not minimum <= value <= maximum:
|
||||
comparator = 'non-negative' if minimum == 0 else 'positive'
|
||||
raise ValueError(f'database.postgresql.{name} must be a {comparator} integer no greater than {maximum}')
|
||||
return value
|
||||
|
||||
host = postgresql_config.get('host', '127.0.0.1')
|
||||
port = postgresql_config.get('port', 5432)
|
||||
user = postgresql_config.get('user', 'postgres')
|
||||
password = postgresql_config.get('password', 'postgres')
|
||||
database = postgresql_config.get('database', 'postgres')
|
||||
engine_url = f'postgresql+asyncpg://{user}:{password}@{host}:{port}/{database}'
|
||||
self.engine = sqlalchemy_asyncio.create_async_engine(engine_url)
|
||||
async def initialize(self) -> None:
|
||||
self._pool_timeouts_total = 0
|
||||
postgresql_config = self.ap.instance_config.data.get('database', {}).get('postgresql', {})
|
||||
if not isinstance(postgresql_config, dict):
|
||||
raise ValueError('database.postgresql must be an object')
|
||||
if self.url_override is not None:
|
||||
engine_url = self.url_override
|
||||
else:
|
||||
explicit_url = postgresql_config.get('url')
|
||||
if explicit_url:
|
||||
if not isinstance(explicit_url, str):
|
||||
raise ValueError('database.postgresql.url must be a string')
|
||||
try:
|
||||
engine_url = sqlalchemy.engine.make_url(explicit_url)
|
||||
except Exception:
|
||||
raise ValueError('database.postgresql.url is invalid') from None
|
||||
try:
|
||||
engine_url = normalize_asyncpg_url(engine_url)
|
||||
except ValueError:
|
||||
raise ValueError('database.postgresql.url must use valid PostgreSQL asyncpg options') from None
|
||||
else:
|
||||
engine_url = sqlalchemy.URL.create(
|
||||
'postgresql+asyncpg',
|
||||
username=postgresql_config.get('user', 'postgres'),
|
||||
password=postgresql_config.get('password', 'postgres'),
|
||||
host=postgresql_config.get('host', '127.0.0.1'),
|
||||
port=postgresql_config.get('port', 5432),
|
||||
database=postgresql_config.get('database', 'postgres'),
|
||||
)
|
||||
self.pool_size = self._pool_integer(
|
||||
postgresql_config,
|
||||
'pool_size',
|
||||
10,
|
||||
minimum=1,
|
||||
maximum=MAX_POOL_CONNECTIONS,
|
||||
)
|
||||
self.max_overflow = self._pool_integer(
|
||||
postgresql_config,
|
||||
'max_overflow',
|
||||
10,
|
||||
minimum=0,
|
||||
maximum=MAX_POOL_CONNECTIONS,
|
||||
)
|
||||
if self.pool_size + self.max_overflow > MAX_POOL_CONNECTIONS:
|
||||
raise ValueError(f'database.postgresql pool_size + max_overflow must not exceed {MAX_POOL_CONNECTIONS}')
|
||||
self.pool_timeout_seconds = self._pool_integer(
|
||||
postgresql_config,
|
||||
'pool_timeout_seconds',
|
||||
30,
|
||||
minimum=1,
|
||||
maximum=MAX_POOL_TIMEOUT_SECONDS,
|
||||
)
|
||||
self.pool_recycle_seconds = self._pool_integer(
|
||||
postgresql_config,
|
||||
'pool_recycle_seconds',
|
||||
1800,
|
||||
minimum=1,
|
||||
maximum=MAX_POOL_RECYCLE_SECONDS,
|
||||
)
|
||||
connect_args = {}
|
||||
self.statement_timeout_ms = 0
|
||||
self.lock_timeout_ms = 0
|
||||
self.idle_transaction_timeout_ms = 0
|
||||
if self.persistence_mode == 'cloud_runtime':
|
||||
self.statement_timeout_ms = self._pool_integer(
|
||||
postgresql_config,
|
||||
'statement_timeout_ms',
|
||||
60_000,
|
||||
minimum=1,
|
||||
maximum=MAX_STATEMENT_TIMEOUT_MS,
|
||||
)
|
||||
self.lock_timeout_ms = self._pool_integer(
|
||||
postgresql_config,
|
||||
'lock_timeout_ms',
|
||||
5_000,
|
||||
minimum=1,
|
||||
maximum=MAX_LOCK_TIMEOUT_MS,
|
||||
)
|
||||
self.idle_transaction_timeout_ms = self._pool_integer(
|
||||
postgresql_config,
|
||||
'idle_in_transaction_session_timeout_ms',
|
||||
60_000,
|
||||
minimum=1,
|
||||
maximum=MAX_IDLE_TRANSACTION_TIMEOUT_MS,
|
||||
)
|
||||
connect_args = {
|
||||
'server_settings': {
|
||||
'statement_timeout': str(self.statement_timeout_ms),
|
||||
'lock_timeout': str(self.lock_timeout_ms),
|
||||
'idle_in_transaction_session_timeout': str(self.idle_transaction_timeout_ms),
|
||||
}
|
||||
}
|
||||
self.engine = sqlalchemy_asyncio.create_async_engine(
|
||||
engine_url,
|
||||
pool_size=self.pool_size,
|
||||
max_overflow=self.max_overflow,
|
||||
pool_timeout=self.pool_timeout_seconds,
|
||||
pool_recycle=self.pool_recycle_seconds,
|
||||
pool_pre_ping=True,
|
||||
**({'connect_args': connect_args} if connect_args else {}),
|
||||
)
|
||||
|
||||
def resource_stats(self) -> dict[str, int]:
|
||||
"""Return aggregate pool gauges without exposing connection details."""
|
||||
|
||||
pool = self.engine.pool
|
||||
|
||||
def read(name: str) -> int:
|
||||
method = getattr(pool, name, None)
|
||||
if not callable(method):
|
||||
return 0
|
||||
try:
|
||||
return int(method())
|
||||
except Exception:
|
||||
return 0
|
||||
|
||||
return {
|
||||
'configured_size': self.pool_size,
|
||||
'configured_max_overflow': self.max_overflow,
|
||||
'configured_capacity': self.pool_size + self.max_overflow,
|
||||
'statement_timeout_ms': self.statement_timeout_ms,
|
||||
'lock_timeout_ms': self.lock_timeout_ms,
|
||||
'idle_in_transaction_session_timeout_ms': self.idle_transaction_timeout_ms,
|
||||
'timeouts_total': self._pool_timeouts_total,
|
||||
'checked_in': read('checkedin'),
|
||||
'checked_out': read('checkedout'),
|
||||
'overflow': max(read('overflow'), 0),
|
||||
}
|
||||
|
||||
def record_pool_timeout(self) -> None:
|
||||
self._pool_timeouts_total += 1
|
||||
|
||||
Reference in New Issue
Block a user