fix(cloud): render empty skills without sandbox grant

docs/multi-tenant/DATABASE_MIGRATION_GUIDE.md

@@ -1,166 +0,0 @@
-# LangBot 多租户数据库迁移指南
-
-## 概述
-
-LangBot 从单租户 OSS 架构迁移到多租户 SaaS 架构，需要执行 7 个数据库迁移（0009-0015）。
-
-## 迁移序列
-
-```
-0009_workspace_tenancy_kernel → 创建 Workspace、成员、邀请表
-0010_scope_tenant_resources → 所有业务表添加 workspace_uuid
-0011_postgres_tenant_rls → PostgreSQL 行级安全策略
-0012_plugin_installation_identity → 插件实例租户绑定
-0013_tenant_pgvector → RAG 向量存储隔离
-0014_cloud_directory_projection → Cloud 控制平面同步
-0015_cloud_core_collaboration → 协作和权限功能
-```
-
-## 执行步骤
-
-### 1. 备份（必须）
-
-```bash
-# SQLite
-cp ~/.langbot/data/langbot.db ~/.langbot/data/langbot.db.backup-$(date +%Y%m%d)
-
-# PostgreSQL  
-pg_dump -U langbot_user -d langbot_db -F c -f langbot_backup_$(date +%Y%m%d).dump
-```
-
-### 2. 执行迁移
-
-```bash
-# 停止服务
-sudo -S -p '' systemctl stop langbot
-
-# 执行迁移
-python -m langbot.pkg.persistence.migration upgrade head
-
-# 验证
-python -m langbot.pkg.persistence.migration current
-# 预期: 0015_cloud_core_collaboration
-
-# 启动服务
-sudo -S -p '' systemctl start langbot
-```
-
-### 3. OSS 单租户自动迁移
-
-迁移会自动：
-- 创建默认 Workspace（名称："Default Workspace"）
-- 第一个用户成为 Owner
-- 所有现有资源绑定到该 Workspace
-
-### 4. 验证检查
-
-```bash
-# 检查 Workspace
-python << EOF
-from langbot.pkg.persistence import manager
-import sqlalchemy as sa
-
-with manager.engine.connect() as conn:
-    ws = conn.execute(sa.text("SELECT uuid, name FROM workspaces LIMIT 1")).first()
-    print(f"Workspace: {ws[1]} ({ws[0]})")
-    
-    # 检查资源绑定
-    bot_count = conn.execute(sa.text(
-        f"SELECT COUNT(*) FROM bots WHERE workspace_uuid='{ws[0]}'"
-    )).scalar()
-    print(f"Bots: {bot_count}")
-EOF
-```
-
-## 回滚方案
-
-### 完全回滚（丢失多租户数据）
-
-```bash
-# 1. 停止服务
-sudo -S -p '' systemctl stop langbot
-
-# 2. 恢复备份
-cp ~/.langbot/data/langbot.db.backup-YYYYMMDD ~/.langbot/data/langbot.db
-
-# 3. 回退代码
-git checkout v4.10.x
-pip install -e .
-
-# 4. 启动
-sudo -S -p '' systemctl start langbot
-```
-
-### 降级迁移（保留数据但移除多租户）
-
-```bash
-# 警告：会移除 Workspace 表但保留资源
-python -m langbot.pkg.persistence.migration downgrade 0008_mcp_resource_prefs
-```
-
-## 常见问题
-
-### Q: 迁移后无法登录
-
-```bash
-# 检查用户 UUID
-python << EOF
-from langbot.pkg.persistence import manager
-import sqlalchemy as sa
-
-with manager.engine.connect() as conn:
-    users = conn.execute(sa.text("SELECT id, user, uuid, status FROM users")).all()
-    for u in users:
-        print(f"{u[1]}: UUID={u[2]}, Status={u[3]}")
-EOF
-```
-
-### Q: 资源看不见了
-
-检查 Workspace 上下文：
-```bash
-# 前端请求需要带 X-Workspace-ID header
-curl -H "Authorization: Bearer $TOKEN" \
-     -H "X-Workspace-ID: $WORKSPACE_UUID" \
-     http://localhost:5200/api/v1/platform/bots
-```
-
-### Q: 迁移速度慢
-
-```bash
-# SQLite 优化
-sqlite3 ~/.langbot/data/langbot.db << EOF
-PRAGMA journal_mode=WAL;
-PRAGMA synchronous=NORMAL;
-VACUUM;
-EOF
-```
-
-## 性能调优
-
-### PostgreSQL 索引
-
-```sql
--- 迁移后创建
-CREATE INDEX CONCURRENTLY idx_model_providers_workspace 
-    ON model_providers(workspace_uuid);
-
-CREATE INDEX CONCURRENTLY idx_bots_workspace 
-    ON bots(workspace_uuid);
-
-CREATE INDEX CONCURRENTLY idx_pipelines_workspace 
-    ON pipelines(workspace_uuid);
-```
-
-## 预估时间
-
-- SQLite < 100MB: 2-5 分钟
-- SQLite 100MB-1GB: 5-15 分钟  
-- PostgreSQL: < 5 分钟（取决于数据量）
-
-## 支持
-
-问题反馈：https://github.com/langbot-app/LangBot/issues
-
-**版本**: 1.0  
-**最后更新**: 2026-07-30

src/langbot/pkg/api/http/controller/groups/files.py

@@ -23,13 +23,8 @@ def _storage_owner(context: RequestContext) -> str:
 @group.group_class('files', '/api/v1/files')
 class FilesRouterGroup(group.RouterGroup):
     async def initialize(self) -> None:
-        @self.route(
-            '/image/<path:image_key>',
-            methods=['GET'],
-            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
-            permission=Permission.RESOURCE_VIEW,
-        )
-        async def _(image_key: str, request_context: RequestContext) -> quart.Response:
+        @self.route('/image/<path:image_key>', methods=['GET'], auth_type=group.AuthType.NONE)
+        async def _(image_key: str) -> quart.Response:
             image_bytes = await self.ap.storage_mgr.resolve_public_object(
                 image_key,
                 expected_owner_type='upload_image',

src/langbot/pkg/api/http/controller/groups/pipelines/websocket_chat.py

@@ -128,7 +128,7 @@ class WebSocketChatRouterGroup(group.RouterGroup):
         self,
         request_context: RequestContext,
         token: str,
-    ) -> RequestContext:
+    ) -> None:
         """Recheck revocable account, membership, permission, and placement state."""
 
         account, _ = await self._authenticate_account(token)
@@ -168,7 +168,6 @@ class WebSocketChatRouterGroup(group.RouterGroup):
             entitlement_revision=request_context.entitlement_revision,
         )
         require_permission(current_context, Permission.RUNTIME_OPERATE)
-        return current_context
 
     async def _get_scoped_adapter(self, request_context: RequestContext, pipeline_uuid: str):
         pipeline = await run_in_workspace_uow(

src/langbot/pkg/api/http/controller/groups/skills.py

@@ -2,7 +2,6 @@ from __future__ import annotations
 
 import quart
 
-from langbot.pkg.cloud.entitlements import EntitlementFeatureUnavailableError
 from langbot_plugin.box.errors import BoxError
 
 from ...authz import Permission
@@ -24,11 +23,6 @@ class SkillsRouterGroup(group.RouterGroup):
         async def list_skills(request_context: RequestContext) -> quart.Response:
             try:
                 skills = await self.ap.skill_service.list_skills(request_context)
-            except EntitlementFeatureUnavailableError:
-                # Plans without managed sandbox support have no runnable skills.
-                # Treat that capability absence as an empty collection so the
-                # shared UI can render normally instead of surfacing a 500.
-                return self.success(data={'skills': []})
             except (ValueError, BoxError) as exc:
                 return self.http_status(400, -1, str(exc))
             return self.success(data={'skills': skills})

src/langbot/pkg/api/http/service/knowledge.py

@@ -56,14 +56,6 @@ class KnowledgeService:
         require_workspace_uuid(context)
         # In new architecture, we delegate entirely to RAGManager which uses plugins.
         # Legacy internal KB creation is removed.
-        limitation = (
-            getattr(getattr(self.ap, 'instance_config', None), 'data', {}).get('system', {}).get('limitation', {})
-        )
-        max_knowledge_bases = limitation.get('max_knowledge_bases', -1)
-        if max_knowledge_bases >= 0:
-            knowledge_bases = await self.ap.rag_mgr.get_all_knowledge_base_details(context)
-            if len(knowledge_bases) >= max_knowledge_bases:
-                raise ValueError(f'Maximum number of knowledge bases ({max_knowledge_bases}) reached')
 
         knowledge_engine_plugin_id = kb_data.get('knowledge_engine_plugin_id')
         if not knowledge_engine_plugin_id:

src/langbot/pkg/api/http/service/provider.py

@@ -331,15 +331,8 @@ class ModelProviderService:
         embedding_models = await self.ap.embedding_models_service.get_embedding_models_by_provider(
             context, provider_uuid
         )
-        rerank_service = getattr(self.ap, 'rerank_models_service', None)
-        rerank_models = (
-            await rerank_service.get_rerank_models_by_provider(context, provider_uuid)
-            if rerank_service is not None
-            else []
-        )
         existing_llm_names = {model['name'] for model in llm_models}
         existing_embedding_names = {model['name'] for model in embedding_models}
-        existing_rerank_names = {model['name'] for model in rerank_models}
 
         filtered_models = []
         for model in scanned_models:
@@ -366,8 +359,6 @@ class ModelProviderService:
                     'already_added': (
                         model_name in existing_embedding_names
                         if scanned_type == 'embedding'
-                        else model_name in existing_rerank_names
-                        if scanned_type == 'rerank'
                         else model_name in existing_llm_names
                     ),
                 }

src/langbot/pkg/api/http/service/skill.py

@@ -12,6 +12,7 @@ from urllib.parse import quote, unquote, urlparse
 
 import httpx
 
+from ....cloud.entitlements import EntitlementFeatureUnavailableError
 from ....core import app
 from ....skill.utils import parse_frontmatter
 from ....utils import httpclient
@@ -119,7 +120,13 @@ class SkillService:
         box_service = self._box_service()
         if box_service is None:
             return []
-        return [self._serialize_skill(skill) for skill in await box_service.list_skills(execution_context)]
+        try:
+            skills = await box_service.list_skills(execution_context)
+        except EntitlementFeatureUnavailableError as error:
+            if error.feature == 'managed_sandbox':
+                return []
+            raise
+        return [self._serialize_skill(skill) for skill in skills]
 
     async def get_skill(self, context: TenantContext, skill_name: str) -> Optional[dict]:
         execution_context = await self._execution_context(context)

src/langbot/pkg/cloud/entitlements.py

@@ -18,19 +18,11 @@ class EntitlementUnavailableError(RuntimeError):
 
 
 class EntitlementFeatureUnavailableError(EntitlementUnavailableError):
-    """Raised only when an active entitlement does not grant one feature."""
+    """Raised when an active entitlement explicitly omits a capability."""
 
-    def __init__(
-        self,
-        feature: str,
-        *,
-        entitlement_revision: int | None = None,
-    ) -> None:
+    def __init__(self, message: str, *, feature: str, entitlement_revision: int | None = None) -> None:
+        super().__init__(message, entitlement_revision=entitlement_revision)
         self.feature = feature
-        super().__init__(
-            f'Workspace entitlement does not grant {feature}',
-            entitlement_revision=entitlement_revision,
-        )
 
 
 class EntitlementSnapshot(pydantic.BaseModel):
@@ -99,7 +91,8 @@ class EntitlementSnapshot(pydantic.BaseModel):
     def require_feature(self, feature: str) -> None:
         if self.features.get(feature) is not True:
             raise EntitlementFeatureUnavailableError(
-                feature,
+                f'Workspace entitlement does not grant {feature}',
+                feature=feature,
                 entitlement_revision=self.entitlement_revision,
             )
 

src/langbot/pkg/pipeline/process/handlers/command.py

@@ -1,12 +1,10 @@
 from __future__ import annotations
 import typing
 
-import sqlalchemy
 
 from .. import handler
 from ... import entities
 from ... import plugin_diagnostics
-from ....entity.persistence.bot import BotAdmin
 import langbot_plugin.api.entities.builtin.provider.message as provider_message
 import langbot_plugin.api.entities.builtin.provider.session as provider_session
 import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
@@ -26,14 +24,7 @@ class CommandHandler(handler.MessageHandler):
 
         privilege = 1
 
-        admins = await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.select(BotAdmin).where(
-                BotAdmin.bot_uuid == (query.bot_uuid or ''),
-                BotAdmin.launcher_type == query.launcher_type.value,
-                BotAdmin.launcher_id == str(query.launcher_id),
-            )
-        )
-        if admins.first() is not None:
+        if f'{query.launcher_type.value}_{query.launcher_id}' in self.ap.instance_config.data['admins']:
             privilege = 2
 
         spt = command_text.split(' ')

src/langbot/pkg/platform/sources/aiocqhttp.py

@@ -241,11 +241,7 @@ class AiocqhttpMessageConverter(abstract_platform_adapter.AbstractMessageConvert
         async def process_message_data(msg_data, reply_list):
             if msg_data['type'] == 'image':
                 image_base64, image_format = await image.qq_image_url_to_base64(msg_data['data']['url'])
-                reply_list.append(
-                    platform_message.Image(
-                        url=msg_data['data']['url'], base64=f'data:image/{image_format};base64,{image_base64}'
-                    )
-                )
+                reply_list.append(platform_message.Image(base64=f'data:image/{image_format};base64,{image_base64}'))
 
             elif msg_data['type'] == 'text':
                 reply_list.append(platform_message.Plain(text=msg_data['data']['text']))
@@ -290,9 +286,7 @@ class AiocqhttpMessageConverter(abstract_platform_adapter.AbstractMessageConvert
                     image_msg = platform_message.Face(face_id=face_id, face_name=face_name)
                 else:
                     image_base64, image_format = await image.qq_image_url_to_base64(msg.data['url'])
-                    image_msg = platform_message.Image(
-                        url=msg.data['url'], base64=f'data:image/{image_format};base64,{image_base64}'
-                    )
+                    image_msg = platform_message.Image(base64=f'data:image/{image_format};base64,{image_base64}')
                 yiri_msg_list.append(image_msg)
             elif msg.type == 'forward':
                 # 暂时不太合理

src/langbot/pkg/platform/sources/discord.py

@@ -764,9 +764,7 @@ class DiscordMessageConverter(abstract_platform_adapter.AbstractMessageConverter
                 )
                 image_base64 = (await asyncio.to_thread(base64.b64encode, image_data)).decode('utf-8')
                 image_format = response.headers['Content-Type']
-                element_list.append(
-                    platform_message.Image(url=attachment.url, base64=f'data:{image_format};base64,{image_base64}')
-                )
+                element_list.append(platform_message.Image(base64=f'data:{image_format};base64,{image_base64}'))
 
         return platform_message.MessageChain(element_list)
 

src/langbot/pkg/platform/sources/qqofficial.py

@@ -102,7 +102,7 @@ class QQOfficialMessageConverter(abstract_platform_adapter.AbstractMessageConver
         yiri_msg_list.append(platform_message.Source(id=message_id, time=datetime.datetime.now()))
         if pic_url is not None:
             base64_url = await image.get_qq_official_image_base64(pic_url=pic_url, content_type=content_type)
-            yiri_msg_list.append(platform_message.Image(url=pic_url, base64=base64_url))
+            yiri_msg_list.append(platform_message.Image(base64=base64_url))
 
         yiri_msg_list.append(platform_message.Plain(text=message))
         chain = platform_message.MessageChain(yiri_msg_list)

src/langbot/pkg/platform/sources/slack.py

@@ -47,7 +47,7 @@ class SlackMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
         yiri_msg_list.append(platform_message.Source(id=message_id, time=datetime.datetime.now()))
         if pic_url is not None:
             base64_url = await image.get_slack_image_to_base64(pic_url=pic_url, bot_token=bot.bot_token)
-            yiri_msg_list.append(platform_message.Image(url=pic_url, base64=base64_url))
+            yiri_msg_list.append(platform_message.Image(base64=base64_url))
 
         yiri_msg_list.append(platform_message.Plain(text=message))
         chain = platform_message.MessageChain(yiri_msg_list)

src/langbot/pkg/platform/sources/telegram.py

@@ -181,10 +181,7 @@ class TelegramMessageConverter(abstract_platform_adapter.AbstractMessageConverte
 
             encoded = await asyncio.to_thread(base64.b64encode, file_bytes)
             message_components.append(
-                platform_message.Image(
-                    url=file.file_path,
-                    base64=f'data:{file_format};base64,{encoded.decode("utf-8")}',
-                )
+                platform_message.Image(base64=f'data:{file_format};base64,{encoded.decode("utf-8")}')
             )
 
         if message.voice:

src/langbot/pkg/platform/sources/wecom.py

@@ -133,9 +133,7 @@ class WecomMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
         yiri_msg_list = []
         yiri_msg_list.append(platform_message.Source(id=message_id, time=datetime.datetime.now()))
         image_base64, image_format = await image.get_wecom_image_base64(pic_url=picurl)
-        yiri_msg_list.append(
-            platform_message.Image(url=picurl, base64=f'data:image/{image_format};base64,{image_base64}')
-        )
+        yiri_msg_list.append(platform_message.Image(base64=f'data:image/{image_format};base64,{image_base64}'))
         chain = platform_message.MessageChain(yiri_msg_list)
 
         return chain

src/langbot/pkg/provider/modelmgr/modelmgr.py

@@ -529,7 +529,6 @@ class ModelManager:
             model['uuid']: model
             for model in await self.ap.embedding_models_service.get_embedding_models(context, include_secret=True)
         }
-        existing_rerank_models = {m['uuid']: m for m in await self.ap.rerank_models_service.get_rerank_models(context)}
 
         created = 0
         updated = 0
@@ -598,36 +597,6 @@ class ModelManager:
                         )
                         updated += 1
 
-            elif space_model.category == 'rerank':
-                existing = existing_rerank_models.get(space_model.uuid)
-                if existing is None:
-                    await self.ap.rerank_models_service.create_rerank_model(
-                        context,
-                        {
-                            'uuid': space_model.uuid,
-                            'name': space_model.model_id,
-                            'provider_uuid': space_model_provider.uuid,
-                            'extra_args': {},
-                            'prefered_ranking': space_model.featured_order,
-                        },
-                        preserve_uuid=True,
-                    )
-                    created += 1
-                elif existing.get('provider_uuid') == space_model_provider.uuid:
-                    desired = {
-                        'name': space_model.model_id,
-                        'provider_uuid': space_model_provider.uuid,
-                        'prefered_ranking': space_model.featured_order,
-                    }
-                    if (
-                        existing.get('name') != desired['name']
-                        or existing.get('prefered_ranking') != desired['prefered_ranking']
-                    ):
-                        await self.ap.rerank_models_service.update_rerank_model(
-                            context, space_model.uuid, dict(desired)
-                        )
-                        updated += 1
-
         if created or updated:
             self.ap.logger.info(f'Synced models from LangBot Space: {created} added, {updated} updated.')
 

src/langbot/pkg/provider/modelmgr/requesters/litellmchat.py

@@ -944,21 +944,16 @@ class LiteLLMRequester(requester.ProviderAPIRequester):
         if api_key:
             headers['Authorization'] = f'Bearer {api_key}'
 
-        request_args = dict(extra_args)
-        rerank_url = request_args.pop('rerank_url', None)
-        rerank_path = request_args.pop('rerank_path', 'rerank')
-
         payload: dict[str, typing.Any] = {
             'model': model_name,
             'query': query,
             'documents': documents,
             'top_n': top_n,
         }
-        if request_args:
-            payload.update(request_args)
+        if extra_args:
+            payload.update(extra_args)
 
-        if not rerank_url:
-            rerank_url = f'{base_url}/{str(rerank_path).strip("/")}'
+        rerank_url = f'{base_url}/rerank'
 
         try:
             async with httpx.AsyncClient(

src/langbot/pkg/workspace/collaboration.py

@@ -499,14 +499,14 @@ class WorkspaceCollaborationService:
             return await self._run(operation, session=session)
 
     @asynccontextmanager
-    async def _invitation_lock(self, lock_key: str):
-        """Serialize one token within workspace scope while retaining only active lock entries."""
+    async def _invitation_lock(self, token_digest: str):
+        """Serialize one token while retaining only active lock entries."""
 
         async with self._invitation_locks_guard:
-            entry = self._invitation_locks.get(lock_key)
+            entry = self._invitation_locks.get(token_digest)
             if entry is None:
                 entry = _InvitationLockEntry(lock=asyncio.Lock())
-                self._invitation_locks[lock_key] = entry
+                self._invitation_locks[token_digest] = entry
             entry.users += 1
 
         await entry.lock.acquire()
@@ -517,7 +517,7 @@ class WorkspaceCollaborationService:
             async with self._invitation_locks_guard:
                 entry.users -= 1
                 if entry.users == 0:
-                    self._invitation_locks.pop(lock_key, None)
+                    self._invitation_locks.pop(token_digest, None)
 
     async def revoke_invitation(
         self,

src/langbot/templates/config.yaml

@@ -105,7 +105,6 @@ system:
         max_bots: -1
         max_pipelines: -1
         max_extensions: -1
-        max_knowledge_bases: -1
         # When set to a non-empty string, every pipeline is forced to use this
         # Box sandbox-scope template regardless of its own configuration, and
         # the per-pipeline "Sandbox Scope" selector is locked in the web UI.

tests/integration/api/test_skills_entitlements.py

@@ -1,79 +0,0 @@
-"""Skills API behavior when a workspace plan has no managed sandbox."""
-
-from __future__ import annotations
-
-from types import SimpleNamespace
-from unittest.mock import AsyncMock, Mock
-
-import pytest
-import quart
-
-from langbot.pkg.api.http.controller.groups.skills import SkillsRouterGroup
-from langbot.pkg.cloud.entitlements import (
-    EntitlementFeatureUnavailableError,
-    EntitlementUnavailableError,
-)
-
-pytestmark = pytest.mark.integration
-WORKSPACE_UUID = '11111111-1111-4111-8111-111111111111'
-
-
-@pytest.fixture
-async def skills_api():
-    account = SimpleNamespace(uuid='owner-account', user='owner@example.com')
-    access = SimpleNamespace(
-        workspace=SimpleNamespace(uuid=WORKSPACE_UUID),
-        membership=SimpleNamespace(uuid='member-owner', role='owner', projection_revision=1),
-        execution=SimpleNamespace(instance_uuid='instance-a', placement_generation=1),
-    )
-    application = Mock()
-    application.deployment = SimpleNamespace(multi_workspace_enabled=False)
-    application.persistence_mgr = SimpleNamespace(tenant_uow=None)
-    application.user_service.get_authenticated_account = AsyncMock(return_value=account)
-    application.workspace_collaboration_service.resolve_account_workspace = AsyncMock(return_value=access)
-    application.skill_service.list_skills = AsyncMock(
-        side_effect=EntitlementFeatureUnavailableError(
-            'managed_sandbox',
-            entitlement_revision=1,
-        )
-    )
-
-    quart_app = quart.Quart(__name__)
-    router = SkillsRouterGroup(application, quart_app)
-    await router.initialize()
-    return application, quart_app.test_client()
-
-
-@pytest.mark.asyncio
-async def test_list_skills_is_empty_when_plan_has_no_managed_sandbox(skills_api):
-    application, client = skills_api
-    response = await client.get(
-        '/api/v1/skills',
-        headers={
-            'Authorization': 'Bearer owner-token',
-            'X-Workspace-Id': WORKSPACE_UUID,
-        },
-    )
-
-    assert response.status_code == 200
-    payload = await response.get_json()
-    assert payload['data'] == {'skills': []}
-    application.skill_service.list_skills.assert_awaited_once()
-
-
-@pytest.mark.asyncio
-async def test_list_skills_does_not_hide_other_entitlement_failures(skills_api):
-    application, client = skills_api
-    application.skill_service.list_skills.side_effect = EntitlementUnavailableError(
-        'Workspace entitlement revision rolled back'
-    )
-
-    response = await client.get(
-        '/api/v1/skills',
-        headers={
-            'Authorization': 'Bearer owner-token',
-            'X-Workspace-Id': WORKSPACE_UUID,
-        },
-    )
-
-    assert response.status_code == 500

tests/unit_tests/api/service/test_knowledge_service.py

@@ -34,7 +34,6 @@ class _Rows:
 def _app():
     return SimpleNamespace(
         logger=Mock(),
-        instance_config=SimpleNamespace(data={}),
         rag_mgr=SimpleNamespace(
             get_all_knowledge_base_details=AsyncMock(return_value=[]),
             get_knowledge_base_details=AsyncMock(return_value=None),
@@ -120,21 +119,6 @@ async def test_create_validates_schema_and_binds_context():
     )
 
 
-@pytest.mark.asyncio
-async def test_create_enforces_workspace_knowledge_base_limit():
-    app = _app()
-    app.instance_config.data = {'system': {'limitation': {'max_knowledge_bases': 2}}}
-    app.rag_mgr.get_all_knowledge_base_details.return_value = [{'uuid': 'kb-a'}, {'uuid': 'kb-b'}]
-    service = KnowledgeService(app)
-
-    with pytest.raises(ValueError, match=r'Maximum number of knowledge bases \(2\) reached'):
-        await service.create_knowledge_base(
-            CONTEXT,
-            {'knowledge_engine_plugin_id': 'author/engine'},
-        )
-    app.rag_mgr.create_knowledge_base.assert_not_awaited()
-
-
 @pytest.mark.asyncio
 async def test_update_rejects_guessed_uuid_and_scopes_reload():
     app = _app()

tests/unit_tests/api/service/test_provider_service.py

@@ -833,44 +833,6 @@ class TestModelProviderServiceScanProviderModels:
         assert len(result['models']) == 1
         assert result['models'][0]['type'] == 'llm'
 
-    async def test_scan_provider_marks_existing_rerank_model(self):
-        """Rerank scan results use the rerank service when computing already_added."""
-        ap = SimpleNamespace()
-        ap.persistence_mgr = SimpleNamespace()
-        ap.model_mgr = SimpleNamespace()
-        ap.llm_model_service = SimpleNamespace()
-        ap.embedding_models_service = SimpleNamespace()
-        ap.rerank_models_service = SimpleNamespace()
-
-        provider = _create_mock_provider(provider_uuid='rerank-scan-uuid')
-        ap.persistence_mgr.execute_async = AsyncMock(return_value=_create_mock_result([], first_item=provider))
-        ap.persistence_mgr.serialize_model = Mock(
-            return_value={
-                'uuid': 'rerank-scan-uuid',
-                'name': 'New API',
-                'requester': 'new-api-chat-completions',
-                'base_url': 'https://new-api.example.com/v1',
-                'api_keys': ['key'],
-            }
-        )
-
-        runtime_provider = Mock()
-        runtime_provider.token_mgr.get_token.return_value = 'token'
-        runtime_provider.requester.scan_models = AsyncMock(
-            return_value={'models': [{'id': 'Qwen3-Reranker-8B', 'type': 'rerank'}]}
-        )
-        ap.model_mgr.load_provider = AsyncMock(return_value=runtime_provider)
-        ap.llm_model_service.get_llm_models_by_provider = AsyncMock(return_value=[])
-        ap.embedding_models_service.get_embedding_models_by_provider = AsyncMock(return_value=[])
-        ap.rerank_models_service.get_rerank_models_by_provider = AsyncMock(return_value=[{'name': 'Qwen3-Reranker-8B'}])
-
-        result = await ModelProviderService(ap).scan_provider_models(
-            WORKSPACE_UUID, 'rerank-scan-uuid', model_type='rerank'
-        )
-
-        assert result['models'][0]['type'] == 'rerank'
-        assert result['models'][0]['already_added'] is True
-
     async def test_scan_provider_not_implemented_raises_error(self):
         """Raises ValueError when scan not implemented."""
         # Setup

tests/unit_tests/api/service/test_space_service.py

@@ -756,7 +756,7 @@ class TestSpaceServiceGetModels:
                             'uuid': 'uuid-2',
                             'model_id': 'model-2',
                             'provider': 'provider-2',
-                            'category': 'rerank',
+                            'category': 'chat',
                             'status': 'active',
                         },
                     ]
@@ -778,7 +778,6 @@ class TestSpaceServiceGetModels:
 
         # Verify
         assert len(result) == 2
-        assert result[1].category == 'rerank'
 
     async def test_get_models_api_error(self):
         """Raises ValueError on API error."""

tests/unit_tests/pipeline/test_command_handler.py

@@ -158,21 +158,17 @@ class TestCommandHandlerReal:
 
     @pytest.mark.asyncio
     async def test_admin_privilege_check(self, fake_app, mock_event_ctx, mock_execute_factory):
-        """A per-bot admin from the database is marked as admin in command events."""
+        """Admin users get privilege level 2."""
         from langbot_plugin.api.entities.builtin.provider.session import LauncherTypes
 
         command = get_command_handler()
 
-        admin_result = Mock()
-        admin_result.first.return_value = Mock()
-        fake_app.persistence_mgr.execute_async = AsyncMock(return_value=admin_result)
-        fake_app.instance_config.data = {}
+        fake_app.instance_config.data = {'admins': ['person_12345']}
         fake_app.plugin_connector.emit_event = AsyncMock(return_value=mock_event_ctx)
         fake_app.cmd_mgr.execute = mock_execute_factory()
 
         handler = command.CommandHandler(fake_app)
         query = command_query('status')
-        query.bot_uuid = 'bot-1'
         query.launcher_type = LauncherTypes.PERSON
         query.launcher_id = 12345
 
@@ -180,28 +176,23 @@ class TestCommandHandlerReal:
         async for result in handler.handle(query):
             results.append(result)
 
-        fake_app.persistence_mgr.execute_async.assert_awaited_once()
         call_args = fake_app.plugin_connector.emit_event.call_args
         event = call_args[0][0]
         assert event.is_admin is True
 
     @pytest.mark.asyncio
     async def test_non_admin_privilege_check(self, fake_app, mock_event_ctx, mock_execute_factory):
-        """A launcher absent from the per-bot admin table is not an admin."""
+        """Non-admin users get privilege level 1."""
         from langbot_plugin.api.entities.builtin.provider.session import LauncherTypes
 
         command = get_command_handler()
 
-        admin_result = Mock()
-        admin_result.first.return_value = None
-        fake_app.persistence_mgr.execute_async = AsyncMock(return_value=admin_result)
-        fake_app.instance_config.data = {}
+        fake_app.instance_config.data = {'admins': ['person_12345']}
         fake_app.plugin_connector.emit_event = AsyncMock(return_value=mock_event_ctx)
         fake_app.cmd_mgr.execute = mock_execute_factory()
 
         handler = command.CommandHandler(fake_app)
         query = command_query('status')
-        query.bot_uuid = 'bot-1'
         query.launcher_type = LauncherTypes.PERSON
         query.launcher_id = 67890
 
@@ -209,7 +200,6 @@ class TestCommandHandlerReal:
         async for result in handler.handle(query):
             results.append(result)
 
-        fake_app.persistence_mgr.execute_async.assert_awaited_once()
         call_args = fake_app.plugin_connector.emit_event.call_args
         event = call_args[0][0]
         assert event.is_admin is False

tests/unit_tests/provider/test_litellmchat.py

@@ -1147,46 +1147,6 @@ class TestInvokeRerank:
         assert results[0]['relevance_score'] == 1.0
         assert results[1]['relevance_score'] == 0.0
 
-    @pytest.mark.asyncio
-    @pytest.mark.parametrize(
-        ('model_extra_args', 'expected_url'),
-        [
-            ({'rerank_path': 'reranks'}, 'https://gateway.example.com/v1/reranks'),
-            ({'rerank_url': 'https://rerank.example.com/api/rerank'}, 'https://rerank.example.com/api/rerank'),
-        ],
-    )
-    async def test_invoke_rerank_openai_compatible_endpoint_override(self, model_extra_args, expected_url):
-        """Endpoint configuration controls routing and is not sent in the Cohere body."""
-        requester = litellmchat.LiteLLMRequester(
-            ap=Mock(),
-            config={
-                'base_url': 'https://gateway.example.com/v1/',
-                'custom_llm_provider': 'openai',
-            },
-        )
-        model = MockRuntimeRerankModel('Qwen3-Reranker-8B', 'test-api-key')
-        model.model_entity.extra_args = model_extra_args
-
-        mock_resp = Mock()
-        mock_resp.raise_for_status = Mock()
-        mock_resp.json = Mock(return_value={'results': [{'index': 0, 'relevance_score': 0.8}]})
-        mock_client = AsyncMock()
-        mock_client.post = AsyncMock(return_value=mock_resp)
-        mock_client.__aenter__ = AsyncMock(return_value=mock_client)
-        mock_client.__aexit__ = AsyncMock(return_value=False)
-
-        with patch('httpx.AsyncClient', return_value=mock_client):
-            await requester.invoke_rerank(model=model, query='query', documents=['document'])
-
-        assert mock_client.post.call_args.args[0] == expected_url
-        payload = mock_client.post.call_args.kwargs['json']
-        assert payload == {
-            'model': 'Qwen3-Reranker-8B',
-            'query': 'query',
-            'documents': ['document'],
-            'top_n': 1,
-        }
-
 
 class TestConvertMessages:
     """Test _convert_messages method"""

tests/unit_tests/provider/test_model_manager.py

@@ -86,49 +86,6 @@ async def test_model_manager_skips_legacy_space_sync_in_cloud_runtime(mock_app_f
     app.workspace_service.get_local_execution_binding.assert_not_awaited()
 
 
-@pytest.mark.asyncio
-async def test_sync_new_models_from_space_creates_rerank_models(mock_app_for_modelmgr):
-    """Space rerank entries are discovered and persisted under the shared provider."""
-    app = mock_app_for_modelmgr
-    provider = persistence_model.ModelProvider(
-        uuid='space-provider',
-        name='LangBot Space',
-        requester='space-chat-completions',
-        base_url='https://api.langbot.cloud/v1',
-        api_keys=['space-key'],
-    )
-    app.persistence_mgr.execute_async = AsyncMock(return_value=_make_mock_result([provider], first_item=provider))
-    app.space_service.get_models = AsyncMock(
-        return_value=[
-            SimpleNamespace(
-                uuid='rerank-model-uuid',
-                model_id='Qwen3-Reranker-8B',
-                category='rerank',
-                featured_order=10,
-            )
-        ]
-    )
-    app.llm_model_service.get_llm_models = AsyncMock(return_value=[])
-    app.embedding_models_service.get_embedding_models = AsyncMock(return_value=[])
-    app.rerank_models_service = AsyncMock()
-    app.rerank_models_service.get_rerank_models = AsyncMock(return_value=[])
-
-    model_mgr = ModelManager(app)
-    await model_mgr.sync_new_models_from_space(TEST_EXECUTION_CONTEXT)
-
-    app.rerank_models_service.create_rerank_model.assert_awaited_once_with(
-        TEST_EXECUTION_CONTEXT,
-        {
-            'uuid': 'rerank-model-uuid',
-            'name': 'Qwen3-Reranker-8B',
-            'provider_uuid': 'space-provider',
-            'extra_args': {},
-            'prefered_ranking': 10,
-        },
-        preserve_uuid=True,
-    )
-
-
 # ============================================================================
 # Model Loading Tests
 # ============================================================================

tests/unit_tests/test_skill_service.py

@@ -8,6 +8,7 @@ import pytest
 
 from langbot.pkg.api.http.context import ExecutionContext
 from langbot.pkg.api.http.service.skill import SkillService
+from langbot.pkg.cloud.entitlements import EntitlementFeatureUnavailableError, EntitlementUnavailableError
 
 
 _CONTEXT = ExecutionContext(
@@ -113,6 +114,42 @@ class TestRequireBoxForWrite:
         service = SkillService(self._ap_with_disabled_box())
         assert await service.list_skills(_CONTEXT) == []
 
+    @pytest.mark.asyncio
+    async def test_list_skills_returns_empty_when_managed_sandbox_is_not_granted(self):
+        box_service = SimpleNamespace(
+            available=True,
+            list_skills=AsyncMock(
+                side_effect=EntitlementFeatureUnavailableError(
+                    'Workspace entitlement does not grant managed_sandbox',
+                    feature='managed_sandbox',
+                )
+            ),
+        )
+        service = SkillService(
+            SimpleNamespace(
+                workspace_service=_workspace_service(),
+                box_service=box_service,
+            )
+        )
+
+        assert await service.list_skills(_CONTEXT) == []
+
+    @pytest.mark.asyncio
+    async def test_list_skills_preserves_other_entitlement_failures(self):
+        box_service = SimpleNamespace(
+            available=True,
+            list_skills=AsyncMock(side_effect=EntitlementUnavailableError('control plane unavailable')),
+        )
+        service = SkillService(
+            SimpleNamespace(
+                workspace_service=_workspace_service(),
+                box_service=box_service,
+            )
+        )
+
+        with pytest.raises(EntitlementUnavailableError, match='control plane unavailable'):
+            await service.list_skills(_CONTEXT)
+
     @pytest.mark.asyncio
     async def test_read_skill_file_refused_when_box_unavailable(self):
         service = SkillService(self._ap_with_disabled_box())