mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-09-16 23:07:14 +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
@@ -2,6 +2,7 @@ from __future__ import annotations
|
||||
|
||||
import typing
|
||||
import time
|
||||
import inspect
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
|
||||
@@ -9,6 +10,8 @@ from langbot_plugin.api.entities.events import pipeline_query
|
||||
|
||||
from . import loader as tool_loader
|
||||
from .errors import ToolNotFoundError
|
||||
from ...pipeline.pool import get_query_execution_context
|
||||
from ...api.http.service.tenant import TenantContext
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from ...core import app
|
||||
@@ -33,6 +36,36 @@ class ToolManager:
|
||||
def __init__(self, ap: app.Application):
|
||||
self.ap = ap
|
||||
|
||||
async def _bind_plugin_workspace(self, context: TenantContext) -> None:
|
||||
"""Select the tenant before any plugin catalog lookup.
|
||||
|
||||
Tool discovery happens before invocation, so relying on ``call_tool``
|
||||
to bind the Workspace is too late and can expose another task's
|
||||
catalog in a shared Runtime.
|
||||
"""
|
||||
|
||||
connector = getattr(self.ap, 'plugin_connector', None)
|
||||
require_context = getattr(connector, 'require_workspace_context', None)
|
||||
if require_context is None:
|
||||
return
|
||||
result = require_context(context)
|
||||
if inspect.isawaitable(result):
|
||||
await result
|
||||
|
||||
async def _workspace_sandbox_available(self, context: TenantContext) -> bool:
|
||||
"""Resolve the Workspace capability before exposing sandbox tools."""
|
||||
|
||||
box_service = getattr(self.ap, 'box_service', None)
|
||||
checker = getattr(box_service, 'is_workspace_sandbox_available', None)
|
||||
if not callable(checker):
|
||||
# Compatibility for OSS embedders and isolated manager tests. The
|
||||
# BoxService execution path remains the final authority.
|
||||
return True
|
||||
try:
|
||||
return bool(await checker(context))
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
async def initialize(self):
|
||||
from langbot.pkg.utils import importutil
|
||||
from langbot.pkg.provider.tools import loaders
|
||||
@@ -57,19 +90,24 @@ class ToolManager:
|
||||
|
||||
async def get_all_tools(
|
||||
self,
|
||||
context: TenantContext,
|
||||
bound_plugins: list[str] | None = None,
|
||||
bound_mcp_servers: list[str] | None = None,
|
||||
include_skill_authoring: bool = False,
|
||||
include_mcp_resource_tools: bool = True,
|
||||
) -> list[resource_tool.LLMTool]:
|
||||
await self._bind_plugin_workspace(context)
|
||||
all_functions: list[resource_tool.LLMTool] = []
|
||||
|
||||
all_functions.extend(await self.native_tool_loader.get_tools())
|
||||
if include_skill_authoring:
|
||||
sandbox_available = await self._workspace_sandbox_available(context)
|
||||
if sandbox_available:
|
||||
all_functions.extend(await self.native_tool_loader.get_tools())
|
||||
if include_skill_authoring and sandbox_available:
|
||||
all_functions.extend(await self.skill_tool_loader.get_tools())
|
||||
all_functions.extend(await self.plugin_tool_loader.get_tools(bound_plugins))
|
||||
all_functions.extend(
|
||||
await self.mcp_tool_loader.get_tools(
|
||||
context,
|
||||
bound_mcp_servers,
|
||||
include_resource_tools=include_mcp_resource_tools,
|
||||
)
|
||||
@@ -79,11 +117,13 @@ class ToolManager:
|
||||
|
||||
async def get_tool_catalog(
|
||||
self,
|
||||
context: TenantContext,
|
||||
bound_plugins: list[str] | None = None,
|
||||
bound_mcp_servers: list[str] | None = None,
|
||||
include_skill_authoring: bool = False,
|
||||
include_mcp_resource_tools: bool = False,
|
||||
) -> list[dict[str, typing.Any]]:
|
||||
await self._bind_plugin_workspace(context)
|
||||
catalog: list[dict[str, typing.Any]] = []
|
||||
|
||||
def append_tools(source: str, source_name: str, tools: list[resource_tool.LLMTool]) -> None:
|
||||
@@ -99,13 +139,16 @@ class ToolManager:
|
||||
}
|
||||
)
|
||||
|
||||
append_tools('builtin', 'LangBot', await self.native_tool_loader.get_tools())
|
||||
if include_skill_authoring:
|
||||
sandbox_available = await self._workspace_sandbox_available(context)
|
||||
if sandbox_available:
|
||||
append_tools('builtin', 'LangBot', await self.native_tool_loader.get_tools())
|
||||
if include_skill_authoring and sandbox_available:
|
||||
append_tools('skill', 'LangBot', await self.skill_tool_loader.get_tools())
|
||||
catalog.extend(await self.plugin_tool_loader.get_tool_catalog(bound_plugins))
|
||||
|
||||
if self.mcp_tool_loader:
|
||||
for item in await self.mcp_tool_loader.get_tool_catalog(
|
||||
context,
|
||||
bound_mcp_servers,
|
||||
include_resource_tools=include_mcp_resource_tools,
|
||||
):
|
||||
@@ -113,19 +156,24 @@ class ToolManager:
|
||||
|
||||
return catalog
|
||||
|
||||
async def get_tool_by_name(self, name: str) -> tool_loader.ToolLookupResult | None:
|
||||
async def get_tool_by_name(self, context: TenantContext, name: str) -> tool_loader.ToolLookupResult | None:
|
||||
"""Get tool by name from any active loader."""
|
||||
for active_loader in (
|
||||
self.native_tool_loader,
|
||||
self.plugin_tool_loader,
|
||||
self.mcp_tool_loader,
|
||||
self.skill_tool_loader,
|
||||
):
|
||||
await self._bind_plugin_workspace(context)
|
||||
sandbox_available = await self._workspace_sandbox_available(context)
|
||||
if sandbox_available:
|
||||
tool = await self.native_tool_loader.get_tool(name)
|
||||
if tool:
|
||||
return tool
|
||||
for active_loader in (self.plugin_tool_loader,):
|
||||
tool = await active_loader.get_tool(name)
|
||||
if tool:
|
||||
return tool
|
||||
if sandbox_available:
|
||||
tool = await self.skill_tool_loader.get_tool(name)
|
||||
if tool:
|
||||
return tool
|
||||
|
||||
return None
|
||||
return await self.mcp_tool_loader.get_tool(context, name)
|
||||
|
||||
async def generate_tools_for_openai(self, use_funcs: list[resource_tool.LLMTool]) -> list:
|
||||
tools = []
|
||||
@@ -175,6 +223,7 @@ class ToolManager:
|
||||
|
||||
try:
|
||||
await monitoring_service.record_tool_call(
|
||||
get_query_execution_context(query),
|
||||
tool_name=name,
|
||||
tool_source=source,
|
||||
duration=duration_ms,
|
||||
@@ -231,7 +280,10 @@ class ToolManager:
|
||||
async def execute_func_call(self, name: str, parameters: dict, query: pipeline_query.Query) -> typing.Any:
|
||||
from langbot.pkg.telemetry import features as telemetry_features
|
||||
|
||||
if await self.native_tool_loader.has_tool(name):
|
||||
execution_context = get_query_execution_context(query)
|
||||
await self._bind_plugin_workspace(execution_context)
|
||||
sandbox_available = await self._workspace_sandbox_available(execution_context)
|
||||
if sandbox_available and await self.native_tool_loader.has_tool(name):
|
||||
telemetry_features.increment(query, 'tool_calls', 'native')
|
||||
return await self._invoke_tool_with_monitoring(
|
||||
source='native',
|
||||
@@ -249,7 +301,7 @@ class ToolManager:
|
||||
query=query,
|
||||
invoke=lambda: self.plugin_tool_loader.invoke_tool(name, parameters, query),
|
||||
)
|
||||
if await self.mcp_tool_loader.has_tool(name):
|
||||
if await self.mcp_tool_loader.has_tool(execution_context, name):
|
||||
telemetry_features.increment(query, 'tool_calls', 'mcp')
|
||||
return await self._invoke_tool_with_monitoring(
|
||||
source='mcp',
|
||||
@@ -258,7 +310,7 @@ class ToolManager:
|
||||
query=query,
|
||||
invoke=lambda: self.mcp_tool_loader.invoke_tool(name, parameters, query),
|
||||
)
|
||||
if await self.skill_tool_loader.has_tool(name):
|
||||
if sandbox_available and await self.skill_tool_loader.has_tool(name):
|
||||
telemetry_features.increment(query, 'tool_calls', 'skill')
|
||||
return await self._invoke_tool_with_monitoring(
|
||||
source='skill',
|
||||
|
||||
Reference in New Issue
Block a user