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
@@ -4,6 +4,7 @@ import asyncio
|
||||
import contextlib
|
||||
import json
|
||||
import os
|
||||
import secrets
|
||||
import sys
|
||||
import typing
|
||||
from typing import TYPE_CHECKING
|
||||
@@ -16,6 +17,17 @@ from langbot_plugin.runtime.io.connection import Connection
|
||||
from langbot_plugin.box.client import ActionRPCBoxClient
|
||||
from langbot_plugin.box.errors import BoxRuntimeUnavailableError
|
||||
from langbot_plugin.box.actions import LangBotToBoxAction
|
||||
from langbot_plugin.box.security import (
|
||||
BOX_CONTROL_TOKEN_ENV,
|
||||
BOX_CONTROL_TOKEN_HEADER,
|
||||
BOX_INSTANCE_HEADER,
|
||||
BOX_PLACEMENT_GENERATION_HEADER,
|
||||
BOX_TRUSTED_INSTANCE_ENV,
|
||||
BOX_WORKSPACE_HEADER,
|
||||
normalize_instance_uuid,
|
||||
validate_control_token,
|
||||
)
|
||||
from langbot_plugin.entities.io.context import ActionContext
|
||||
|
||||
from ..utils import platform
|
||||
from ..utils.managed_runtime import ManagedRuntimeConnector
|
||||
@@ -123,6 +135,8 @@ class BoxRuntimeConnector(ManagedRuntimeConnector):
|
||||
self._relay_host = parsed.hostname or '127.0.0.1'
|
||||
self._relay_port = parsed.port or _DEFAULT_PORT
|
||||
self._filtered_box_config = _filter_config_for_runtime(_get_box_config(ap))
|
||||
self._trusted_instance_uuid = normalize_instance_uuid(self.ap.workspace_service.instance_uuid)
|
||||
self._control_token = str(os.environ.get(BOX_CONTROL_TOKEN_ENV) or '').strip()
|
||||
|
||||
def uses_websocket(self) -> bool:
|
||||
"""Whether the connector should use WebSocket to reach the Box runtime.
|
||||
@@ -223,8 +237,11 @@ class BoxRuntimeConnector(ManagedRuntimeConnector):
|
||||
from langbot_plugin.runtime.io.controllers.stdio.client import StdioClientController
|
||||
|
||||
self.ap.logger.info('Use stdio to connect to box runtime')
|
||||
self._ensure_control_token(allow_generate=True)
|
||||
python_path = sys.executable
|
||||
env = os.environ.copy()
|
||||
env[BOX_CONTROL_TOKEN_ENV] = self._control_token
|
||||
env[BOX_TRUSTED_INSTANCE_ENV] = self._trusted_instance_uuid
|
||||
if self._filtered_box_config:
|
||||
env['LANGBOT_BOX_CONFIG'] = json.dumps(self._filtered_box_config)
|
||||
|
||||
@@ -259,7 +276,10 @@ class BoxRuntimeConnector(ManagedRuntimeConnector):
|
||||
"""Launch box server as detached subprocess, then connect via WS (Windows)."""
|
||||
self.ap.logger.info('(windows) Use cmd to launch box runtime and communicate via ws')
|
||||
|
||||
self._ensure_control_token(allow_generate=True)
|
||||
env = os.environ.copy()
|
||||
env[BOX_CONTROL_TOKEN_ENV] = self._control_token
|
||||
env[BOX_TRUSTED_INSTANCE_ENV] = self._trusted_instance_uuid
|
||||
if self._filtered_box_config:
|
||||
env['LANGBOT_BOX_CONFIG'] = json.dumps(self._filtered_box_config)
|
||||
|
||||
@@ -282,6 +302,7 @@ class BoxRuntimeConnector(ManagedRuntimeConnector):
|
||||
|
||||
async def _connect_remote_ws(self) -> None:
|
||||
"""Connect to a remote (or Docker) box server via WebSocket."""
|
||||
self._ensure_control_token(allow_generate=False)
|
||||
ws_url = self._resolve_rpc_ws_url()
|
||||
self.ap.logger.info(f'Use WebSocket to connect to box runtime ({ws_url})')
|
||||
await self._connect_ws(ws_url, 'WebSocket')
|
||||
@@ -325,7 +346,11 @@ class BoxRuntimeConnector(ManagedRuntimeConnector):
|
||||
if self.runtime_disconnect_callback is not None:
|
||||
await self.runtime_disconnect_callback(self)
|
||||
|
||||
ctrl = WebSocketClientController(ws_url=ws_url, make_connection_failed_callback=on_connect_failed)
|
||||
ctrl = WebSocketClientController(
|
||||
ws_url=ws_url,
|
||||
make_connection_failed_callback=on_connect_failed,
|
||||
additional_headers=self.get_control_headers(),
|
||||
)
|
||||
self._ctrl = ctrl
|
||||
self._ctrl_task = asyncio.create_task(
|
||||
ctrl.run(self._make_connection_callback(transport_name, connected, connect_error, self._generation))
|
||||
@@ -339,6 +364,41 @@ class BoxRuntimeConnector(ManagedRuntimeConnector):
|
||||
if connect_error:
|
||||
raise BoxRuntimeUnavailableError(f'box runtime connection failed: {connect_error[0]}')
|
||||
|
||||
def _ensure_control_token(self, *, allow_generate: bool) -> str:
|
||||
if not self._control_token and allow_generate:
|
||||
self._control_token = secrets.token_urlsafe(48)
|
||||
try:
|
||||
self._control_token = validate_control_token(self._control_token)
|
||||
except ValueError as exc:
|
||||
raise BoxRuntimeUnavailableError(
|
||||
f'{BOX_CONTROL_TOKEN_ENV} must be configured with a strong shared secret for an external Box runtime'
|
||||
) from exc
|
||||
return self._control_token
|
||||
|
||||
def get_control_headers(self) -> dict[str, str]:
|
||||
"""Headers for the instance-authenticated RPC control handshake."""
|
||||
|
||||
self._ensure_control_token(allow_generate=False)
|
||||
return {
|
||||
BOX_CONTROL_TOKEN_HEADER: self._control_token,
|
||||
BOX_INSTANCE_HEADER: self._trusted_instance_uuid,
|
||||
}
|
||||
|
||||
def get_relay_headers(
|
||||
self,
|
||||
action_context: ActionContext,
|
||||
) -> dict[str, str]:
|
||||
"""Return authenticated, placement-scoped relay handshake headers."""
|
||||
|
||||
context = ActionContext.model_validate(action_context).without_installation()
|
||||
if context.instance_uuid != self._trusted_instance_uuid:
|
||||
raise BoxRuntimeUnavailableError('Box relay context belongs to another LangBot instance')
|
||||
return {
|
||||
**self.get_control_headers(),
|
||||
BOX_WORKSPACE_HEADER: context.workspace_uuid,
|
||||
BOX_PLACEMENT_GENERATION_HEADER: str(context.placement_generation),
|
||||
}
|
||||
|
||||
def _make_connection_callback(
|
||||
self,
|
||||
transport_name: str,
|
||||
|
||||
Reference in New Issue
Block a user