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
@@ -11,6 +11,7 @@ import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
|
||||
import langbot_plugin.api.entities.builtin.provider.message as provider_message
|
||||
import langbot_plugin.api.entities.builtin.rag.context as rag_context
|
||||
|
||||
from ...pipeline.pool import get_query_execution_context
|
||||
|
||||
rag_combined_prompt_template = """
|
||||
The following are relevant context entries retrieved from the knowledge base.
|
||||
@@ -210,7 +211,7 @@ class LocalAgentRunner(runner.RequestRunner):
|
||||
req_messages.append(
|
||||
provider_message.Message(
|
||||
role='system',
|
||||
content=self.ap.box_service.get_system_guidance(query.query_id),
|
||||
content=self.ap.box_service.get_system_guidance(query),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -223,11 +224,15 @@ class LocalAgentRunner(runner.RequestRunner):
|
||||
) -> list[modelmgr_requester.RuntimeLLMModel]:
|
||||
"""Build ordered list of models to try: primary model + fallback models."""
|
||||
candidates = []
|
||||
execution_context = get_query_execution_context(query)
|
||||
|
||||
# Primary model
|
||||
if query.use_llm_model_uuid:
|
||||
try:
|
||||
primary = await self.ap.model_mgr.get_model_by_uuid(query.use_llm_model_uuid)
|
||||
primary = await self.ap.model_mgr.get_model_by_uuid(
|
||||
execution_context,
|
||||
query.use_llm_model_uuid,
|
||||
)
|
||||
candidates.append(primary)
|
||||
except ValueError:
|
||||
self.ap.logger.warning(f'Primary model {query.use_llm_model_uuid} not found')
|
||||
@@ -236,7 +241,10 @@ class LocalAgentRunner(runner.RequestRunner):
|
||||
fallback_uuids = (query.variables or {}).get('_fallback_model_uuids', [])
|
||||
for fb_uuid in fallback_uuids:
|
||||
try:
|
||||
fb_model = await self.ap.model_mgr.get_model_by_uuid(fb_uuid)
|
||||
fb_model = await self.ap.model_mgr.get_model_by_uuid(
|
||||
execution_context,
|
||||
fb_uuid,
|
||||
)
|
||||
candidates.append(fb_model)
|
||||
except ValueError:
|
||||
self.ap.logger.warning(f'Fallback model {fb_uuid} not found, skipping')
|
||||
@@ -346,12 +354,13 @@ class LocalAgentRunner(runner.RequestRunner):
|
||||
if kb_uuids and user_message_text:
|
||||
# only support text for now
|
||||
all_results: list[rag_context.RetrievalResultEntry] = []
|
||||
execution_context = get_query_execution_context(query)
|
||||
|
||||
kb_engine_plugins: set[str] = set()
|
||||
|
||||
# Retrieve from each knowledge base
|
||||
for kb_uuid in kb_uuids:
|
||||
kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
|
||||
kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(execution_context, kb_uuid)
|
||||
|
||||
if not kb:
|
||||
self.ap.logger.warning(f'Knowledge base {kb_uuid} not found, skipping')
|
||||
@@ -364,6 +373,7 @@ class LocalAgentRunner(runner.RequestRunner):
|
||||
kb_engine_plugins.add(engine_plugin_id)
|
||||
|
||||
result = await kb.retrieve(
|
||||
execution_context,
|
||||
user_message_text,
|
||||
settings={
|
||||
'bot_uuid': query.bot_uuid or '',
|
||||
@@ -398,7 +408,10 @@ class LocalAgentRunner(runner.RequestRunner):
|
||||
)
|
||||
if all_results and rerank_model_uuid:
|
||||
try:
|
||||
rerank_model = await self.ap.model_mgr.get_rerank_model_by_uuid(rerank_model_uuid)
|
||||
rerank_model = await self.ap.model_mgr.get_rerank_model_by_uuid(
|
||||
execution_context,
|
||||
rerank_model_uuid,
|
||||
)
|
||||
rerank_top_k = int(local_agent_config.get('rerank-top-k', 5))
|
||||
|
||||
doc_texts = []
|
||||
@@ -411,6 +424,7 @@ class LocalAgentRunner(runner.RequestRunner):
|
||||
model=rerank_model,
|
||||
query=user_message_text,
|
||||
documents=doc_texts_capped,
|
||||
execution_context=execution_context,
|
||||
)
|
||||
|
||||
scored = sorted(scores, key=lambda x: x.get('relevance_score', 0), reverse=True)
|
||||
|
||||
Reference in New Issue
Block a user