mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-08-10 21:10:59 +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
@@ -19,12 +19,32 @@ from ....provider import runners
|
||||
import langbot_plugin.api.entities.builtin.provider.session as provider_session
|
||||
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
|
||||
import langbot_plugin.api.entities.builtin.provider.message as provider_message
|
||||
from ...pool import get_query_execution_context
|
||||
|
||||
|
||||
importutil.import_modules_in_pkg(runners)
|
||||
|
||||
|
||||
class ChatMessageHandler(handler.MessageHandler):
|
||||
def _response_limit(self, name: str, default: int) -> int:
|
||||
instance_config = getattr(self.ap, 'instance_config', None)
|
||||
data = getattr(instance_config, 'data', {})
|
||||
if not isinstance(data, dict):
|
||||
return default
|
||||
value = data.get('system', {}).get('response_limits', {}).get(name, default)
|
||||
try:
|
||||
return max(int(value), 1)
|
||||
except (TypeError, ValueError):
|
||||
return default
|
||||
|
||||
def _check_response_size(
|
||||
self,
|
||||
result: provider_message.Message | provider_message.MessageChunk,
|
||||
) -> None:
|
||||
content = result.content
|
||||
if isinstance(content, str) and len(content) > self._response_limit('max_generated_chars', 1024 * 1024):
|
||||
raise RuntimeError('Provider response exceeds the configured limit')
|
||||
|
||||
async def handle(
|
||||
self,
|
||||
query: pipeline_query.Query,
|
||||
@@ -86,6 +106,7 @@ class ChatMessageHandler(handler.MessageHandler):
|
||||
query.user_message.content = [event_ctx.event.user_message_alter]
|
||||
|
||||
text_length = 0
|
||||
runner = None
|
||||
try:
|
||||
is_stream = await query.adapter.is_stream_output_supported()
|
||||
except AttributeError:
|
||||
@@ -106,6 +127,7 @@ class ChatMessageHandler(handler.MessageHandler):
|
||||
chunk_count = 0 # Track streaming chunks to reduce excessive logging
|
||||
|
||||
async for result in runner.run(query):
|
||||
self._check_response_size(result)
|
||||
result.resp_message_id = str(resp_message_id)
|
||||
if query.resp_messages:
|
||||
query.resp_messages.pop()
|
||||
@@ -118,6 +140,11 @@ class ChatMessageHandler(handler.MessageHandler):
|
||||
query.resp_messages.append(result)
|
||||
|
||||
chunk_count += 1
|
||||
if chunk_count > self._response_limit(
|
||||
'max_stream_chunks',
|
||||
100_000,
|
||||
):
|
||||
raise RuntimeError('Provider stream exceeds the configured event limit')
|
||||
# Only log every 10th chunk to reduce excessive logging during streaming
|
||||
# This prevents memory overflow from thousands of log entries per conversation
|
||||
# First chunk uses INFO level to confirm connection establishment
|
||||
@@ -144,6 +171,7 @@ class ChatMessageHandler(handler.MessageHandler):
|
||||
|
||||
else:
|
||||
async for result in runner.run(query):
|
||||
self._check_response_size(result)
|
||||
query.resp_messages.append(result)
|
||||
|
||||
summary = self.format_result_log(result)
|
||||
@@ -158,6 +186,10 @@ class ChatMessageHandler(handler.MessageHandler):
|
||||
query.session.using_conversation.messages.append(query.user_message)
|
||||
|
||||
query.session.using_conversation.messages.extend(query.resp_messages)
|
||||
self.ap.sess_mgr.trim_conversation_messages(
|
||||
query.session.using_conversation,
|
||||
max_rounds=query.pipeline_config['ai']['local-agent'].get('max-round', 10),
|
||||
)
|
||||
except Exception as e:
|
||||
error_info = f'{traceback.format_exc()}'
|
||||
self.ap.logger.error(f'Conversation({query.query_id}) Request Failed: {error_info}')
|
||||
@@ -180,6 +212,13 @@ class ChatMessageHandler(handler.MessageHandler):
|
||||
debug_notice=traceback.format_exc(),
|
||||
)
|
||||
finally:
|
||||
if runner is not None:
|
||||
try:
|
||||
close_runner = getattr(runner, 'aclose', None)
|
||||
if close_runner is not None:
|
||||
await close_runner()
|
||||
except Exception as ex:
|
||||
self.ap.logger.warning(f'Failed to close request runner: {ex}')
|
||||
# Telemetry reporting: collect minimal per-query execution info and send asynchronously
|
||||
try:
|
||||
end_ts = time.time()
|
||||
@@ -198,7 +237,10 @@ class ChatMessageHandler(handler.MessageHandler):
|
||||
model_name = None
|
||||
try:
|
||||
if runner_name == 'local-agent' and getattr(query, 'use_llm_model_uuid', None):
|
||||
m = await self.ap.model_mgr.get_model_by_uuid(query.use_llm_model_uuid)
|
||||
m = await self.ap.model_mgr.get_model_by_uuid(
|
||||
get_query_execution_context(query),
|
||||
query.use_llm_model_uuid,
|
||||
)
|
||||
if m and getattr(m, 'model_entity', None):
|
||||
model_name = getattr(m.model_entity, 'name', None)
|
||||
except Exception:
|
||||
|
||||
Reference in New Issue
Block a user