mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-08-09 04:40:57 +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
@@ -5,7 +5,9 @@ import typing
|
||||
import time
|
||||
|
||||
from ...core import app
|
||||
from ...api.http.context import ExecutionContext
|
||||
from ...entity.persistence import model as persistence_model
|
||||
from ...workspace.errors import WorkspaceInvariantError
|
||||
import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
|
||||
from . import token
|
||||
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
|
||||
@@ -16,6 +18,20 @@ LLM_USAGE_QUERY_VARIABLE = '_llm_usage'
|
||||
STREAM_USAGE_QUERY_VARIABLE = '_stream_usage'
|
||||
|
||||
|
||||
def _ensure_same_execution_scope(
|
||||
expected: ExecutionContext,
|
||||
actual: ExecutionContext,
|
||||
*,
|
||||
resource: str,
|
||||
) -> None:
|
||||
if (
|
||||
actual.instance_uuid != expected.instance_uuid
|
||||
or actual.workspace_uuid != expected.workspace_uuid
|
||||
or actual.placement_generation != expected.placement_generation
|
||||
):
|
||||
raise WorkspaceInvariantError(f'{resource} belongs to another Workspace execution scope')
|
||||
|
||||
|
||||
def _store_llm_usage(query: pipeline_query.Query | None, usage_info: dict | None) -> None:
|
||||
"""Store the latest provider usage on the query for upstream action handlers."""
|
||||
if query is None or not usage_info:
|
||||
@@ -39,24 +55,61 @@ class RuntimeProvider:
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
execution_context: ExecutionContext,
|
||||
provider_entity: persistence_model.ModelProvider,
|
||||
token_mgr: token.TokenManager,
|
||||
requester: ProviderAPIRequester,
|
||||
):
|
||||
if provider_entity.workspace_uuid != execution_context.workspace_uuid:
|
||||
raise WorkspaceInvariantError('Provider belongs to another Workspace')
|
||||
self.execution_context = execution_context
|
||||
self.provider_entity = provider_entity
|
||||
self.token_mgr = token_mgr
|
||||
self.requester = requester
|
||||
|
||||
def _validate_invocation(
|
||||
self,
|
||||
model: RuntimeLLMModel | RuntimeEmbeddingModel | RuntimeRerankModel,
|
||||
execution_context: ExecutionContext,
|
||||
) -> None:
|
||||
_ensure_same_execution_scope(self.execution_context, execution_context, resource='Provider invocation')
|
||||
_ensure_same_execution_scope(self.execution_context, model.execution_context, resource='Runtime model')
|
||||
if model.provider is not self:
|
||||
raise WorkspaceInvariantError('Runtime model is attached to another provider')
|
||||
|
||||
def _resolve_llm_execution_context(
|
||||
self,
|
||||
query: pipeline_query.Query | None,
|
||||
execution_context: ExecutionContext | None,
|
||||
) -> ExecutionContext:
|
||||
if query is not None:
|
||||
from ...pipeline.pool import get_query_execution_context
|
||||
|
||||
query_context = get_query_execution_context(query)
|
||||
if execution_context is not None:
|
||||
_ensure_same_execution_scope(
|
||||
query_context,
|
||||
execution_context,
|
||||
resource='Explicit LLM invocation context',
|
||||
)
|
||||
return query_context
|
||||
if execution_context is None:
|
||||
raise WorkspaceInvariantError('LLM invocation requires an ExecutionContext when query is absent')
|
||||
return execution_context
|
||||
|
||||
async def invoke_llm(
|
||||
self,
|
||||
query: pipeline_query.Query,
|
||||
query: pipeline_query.Query | None,
|
||||
model: RuntimeLLMModel,
|
||||
messages: typing.List[provider_message.Message],
|
||||
funcs: typing.List[resource_tool.LLMTool] = None,
|
||||
extra_args: dict[str, typing.Any] = {},
|
||||
remove_think: bool = False,
|
||||
execution_context: ExecutionContext | None = None,
|
||||
) -> provider_message.Message:
|
||||
"""Bridge method for invoking LLM with monitoring"""
|
||||
invocation_context = self._resolve_llm_execution_context(query, execution_context)
|
||||
self._validate_invocation(model, invocation_context)
|
||||
# Start timing for monitoring
|
||||
start_time = time.time()
|
||||
input_tokens = 0
|
||||
@@ -130,14 +183,17 @@ class RuntimeProvider:
|
||||
|
||||
async def invoke_llm_stream(
|
||||
self,
|
||||
query: pipeline_query.Query,
|
||||
query: pipeline_query.Query | None,
|
||||
model: RuntimeLLMModel,
|
||||
messages: typing.List[provider_message.Message],
|
||||
funcs: typing.List[resource_tool.LLMTool] = None,
|
||||
extra_args: dict[str, typing.Any] = {},
|
||||
remove_think: bool = False,
|
||||
execution_context: ExecutionContext | None = None,
|
||||
) -> provider_message.MessageChunk:
|
||||
"""Bridge method for invoking LLM stream with monitoring"""
|
||||
invocation_context = self._resolve_llm_execution_context(query, execution_context)
|
||||
self._validate_invocation(model, invocation_context)
|
||||
# Start timing for monitoring
|
||||
start_time = time.time()
|
||||
status = 'success'
|
||||
@@ -212,6 +268,8 @@ class RuntimeProvider:
|
||||
model: RuntimeEmbeddingModel,
|
||||
input_text: typing.List[str],
|
||||
extra_args: dict[str, typing.Any] = {},
|
||||
*,
|
||||
execution_context: ExecutionContext,
|
||||
knowledge_base_id: str | None = None,
|
||||
query_text: str | None = None,
|
||||
session_id: str | None = None,
|
||||
@@ -219,6 +277,7 @@ class RuntimeProvider:
|
||||
call_type: str | None = None,
|
||||
) -> typing.List[typing.List[float]]:
|
||||
"""Bridge method for invoking embedding with monitoring"""
|
||||
self._validate_invocation(model, execution_context)
|
||||
# Start timing for monitoring
|
||||
start_time = time.time()
|
||||
prompt_tokens = 0
|
||||
@@ -254,6 +313,7 @@ class RuntimeProvider:
|
||||
|
||||
try:
|
||||
await self.requester.ap.monitoring_service.record_embedding_call(
|
||||
execution_context,
|
||||
model_name=model.model_entity.name,
|
||||
prompt_tokens=prompt_tokens,
|
||||
total_tokens=total_tokens,
|
||||
@@ -276,8 +336,11 @@ class RuntimeProvider:
|
||||
query: str,
|
||||
documents: typing.List[str],
|
||||
extra_args: dict[str, typing.Any] = {},
|
||||
*,
|
||||
execution_context: ExecutionContext,
|
||||
) -> typing.List[dict]:
|
||||
"""Bridge method for invoking rerank with monitoring"""
|
||||
self._validate_invocation(model, execution_context)
|
||||
start_time = time.time()
|
||||
status = 'success'
|
||||
|
||||
@@ -316,9 +379,16 @@ class RuntimeLLMModel:
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
execution_context: ExecutionContext,
|
||||
model_entity: persistence_model.LLMModel,
|
||||
provider: RuntimeProvider,
|
||||
):
|
||||
_ensure_same_execution_scope(provider.execution_context, execution_context, resource='LLM model')
|
||||
if model_entity.workspace_uuid != execution_context.workspace_uuid:
|
||||
raise WorkspaceInvariantError('LLM model belongs to another Workspace')
|
||||
if model_entity.provider_uuid != provider.provider_entity.uuid:
|
||||
raise WorkspaceInvariantError('LLM model references another provider')
|
||||
self.execution_context = execution_context
|
||||
self.model_entity = model_entity
|
||||
self.provider = provider
|
||||
|
||||
@@ -334,9 +404,16 @@ class RuntimeEmbeddingModel:
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
execution_context: ExecutionContext,
|
||||
model_entity: persistence_model.EmbeddingModel,
|
||||
provider: RuntimeProvider,
|
||||
):
|
||||
_ensure_same_execution_scope(provider.execution_context, execution_context, resource='Embedding model')
|
||||
if model_entity.workspace_uuid != execution_context.workspace_uuid:
|
||||
raise WorkspaceInvariantError('Embedding model belongs to another Workspace')
|
||||
if model_entity.provider_uuid != provider.provider_entity.uuid:
|
||||
raise WorkspaceInvariantError('Embedding model references another provider')
|
||||
self.execution_context = execution_context
|
||||
self.model_entity = model_entity
|
||||
self.provider = provider
|
||||
|
||||
@@ -352,9 +429,16 @@ class RuntimeRerankModel:
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
execution_context: ExecutionContext,
|
||||
model_entity: persistence_model.RerankModel,
|
||||
provider: RuntimeProvider,
|
||||
):
|
||||
_ensure_same_execution_scope(provider.execution_context, execution_context, resource='Rerank model')
|
||||
if model_entity.workspace_uuid != execution_context.workspace_uuid:
|
||||
raise WorkspaceInvariantError('Rerank model belongs to another Workspace')
|
||||
if model_entity.provider_uuid != provider.provider_entity.uuid:
|
||||
raise WorkspaceInvariantError('Rerank model references another provider')
|
||||
self.execution_context = execution_context
|
||||
self.model_entity = model_entity
|
||||
self.provider = provider
|
||||
|
||||
@@ -379,6 +463,17 @@ class ProviderAPIRequester(metaclass=abc.ABCMeta):
|
||||
async def initialize(self):
|
||||
pass
|
||||
|
||||
async def aclose(self) -> None:
|
||||
"""Release requester-owned clients when its runtime provider retires.
|
||||
|
||||
Most built-in requesters are currently stateless, but provider
|
||||
extensions may own connection pools or background resources. Keeping
|
||||
the lifecycle hook on the base class lets Workspace generation changes
|
||||
and application shutdown retire them deterministically.
|
||||
"""
|
||||
|
||||
return None
|
||||
|
||||
async def scan_models(self, api_key: str | None = None) -> dict[str, typing.Any] | list[dict[str, typing.Any]]:
|
||||
"""Scan models supported by the provider.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user