LightRAG/logs/2025-12-04-11-45-beastmode-retrieval-tenant-stats-fix.md
Raphael MANSUY fe9b8ec02a
tests: stabilize integration tests + skip external services; fix multi-tenant API behavior and idempotency (#4)
* feat: Implement multi-tenant architecture with tenant and knowledge base models

- Added data models for tenants, knowledge bases, and related configurations.
- Introduced role and permission management for users in the multi-tenant system.
- Created a service layer for managing tenants and knowledge bases, including CRUD operations.
- Developed a tenant-aware instance manager for LightRAG with caching and isolation features.
- Added a migration script to transition existing workspace-based deployments to the new multi-tenant architecture.

* chore: ignore lightrag/api/webui/assets/ directory

* chore: stop tracking lightrag/api/webui/assets (ignore in .gitignore)

* feat: Initialize LightRAG Multi-Tenant Stack with PostgreSQL

- Added README.md for project overview, setup instructions, and architecture details.
- Created docker-compose.yml to define services: PostgreSQL, Redis, LightRAG API, and Web UI.
- Introduced env.example for environment variable configuration.
- Implemented init-postgres.sql for PostgreSQL schema initialization with multi-tenant support.
- Added reproduce_issue.py for testing default tenant access via API.

* feat: Enhance TenantSelector and update related components for improved multi-tenant support

* feat: Enhance testing capabilities and update documentation

- Updated Makefile to include new test commands for various modes (compatibility, isolation, multi-tenant, security, coverage, and dry-run).
- Modified API health check endpoint in Makefile to reflect new port configuration.
- Updated QUICK_START.md and README.md to reflect changes in service URLs and ports.
- Added environment variables for testing modes in env.example.
- Introduced run_all_tests.sh script to automate testing across different modes.
- Created conftest.py for pytest configuration, including database fixtures and mock services.
- Implemented database helper functions for streamlined database operations in tests.
- Added test collection hooks to skip tests based on the current MULTITENANT_MODE.

* feat: Implement multi-tenant support with demo mode enabled by default

- Added multi-tenant configuration to the environment and Docker setup.
- Created pre-configured demo tenants (acme-corp and techstart) for testing.
- Updated API endpoints to support tenant-specific data access.
- Enhanced Makefile commands for better service management and database operations.
- Introduced user-tenant membership system with role-based access control.
- Added comprehensive documentation for multi-tenant setup and usage.
- Fixed issues with document visibility in multi-tenant environments.
- Implemented necessary database migrations for user memberships and legacy support.

* feat(audit): Add final audit report for multi-tenant implementation

- Documented overall assessment, architecture overview, test results, security findings, and recommendations.
- Included detailed findings on critical security issues and architectural concerns.

fix(security): Implement security fixes based on audit findings

- Removed global RAG fallback and enforced strict tenant context.
- Configured super-admin access and required user authentication for tenant access.
- Cleared localStorage on logout and improved error handling in WebUI.

chore(logs): Create task logs for audit and security fixes implementation

- Documented actions, decisions, and next steps for both audit and security fixes.
- Summarized test results and remaining recommendations.

chore(scripts): Enhance development stack management scripts

- Added scripts for cleaning, starting, and stopping the development stack.
- Improved output messages and ensured graceful shutdown of services.

feat(starter): Initialize PostgreSQL with AGE extension support

- Created initialization scripts for PostgreSQL extensions including uuid-ossp, vector, and AGE.
- Ensured successful installation and verification of extensions.

* feat: Implement auto-select for first tenant and KB on initial load in WebUI

- Removed WEBUI_INITIAL_STATE_FIX.md as the issue is resolved.
- Added useTenantInitialization hook to automatically select the first available tenant and KB on app load.
- Integrated the new hook into the Root component of the WebUI.
- Updated RetrievalTesting component to ensure a KB is selected before allowing user interaction.
- Created end-to-end tests for multi-tenant isolation and real service interactions.
- Added scripts for starting, stopping, and cleaning the development stack.
- Enhanced API and tenant routes to support tenant-specific pipeline status initialization.
- Updated constants for backend URL to reflect the correct port.
- Improved error handling and logging in various components.

* feat: Add multi-tenant support with enhanced E2E testing scripts and client functionality

* update client

* Add integration and unit tests for multi-tenant API, models, security, and storage

- Implement integration tests for tenant and knowledge base management endpoints in `test_tenant_api_routes.py`.
- Create unit tests for tenant isolation, model validation, and role permissions in `test_tenant_models.py`.
- Add security tests to enforce role-based permissions and context validation in `test_tenant_security.py`.
- Develop tests for tenant-aware storage operations and context isolation in `test_tenant_storage_phase3.py`.

* feat(e2e): Implement OpenAI model support and database reset functionality

* Add comprehensive test suite for gpt-5-nano compatibility

- Introduced tests for parameter normalization, embeddings, and entity extraction.
- Implemented direct API testing for gpt-5-nano.
- Validated .env configuration loading and OpenAI API connectivity.
- Analyzed reasoning token overhead with various token limits.
- Documented test procedures and expected outcomes in README files.
- Ensured all tests pass for production readiness.

* kg(postgres_impl): ensure AGE extension is loaded in session and configure graph initialization

* dev: add hybrid dev helper scripts, Makefile, docker-compose.dev-db and local development docs

* feat(dev): add dev helper scripts and local development documentation for hybrid setup

* feat(multi-tenant): add detailed specifications and logs for multi-tenant improvements, including UX, backend handling, and ingestion pipeline

* feat(migration): add generated tenant/kb columns, indexes, triggers; drop unused tables; update schema and docs

* test(backward-compat): adapt tests to new StorageNameSpace/TenantService APIs (use concrete dummy storages)

* chore: multi-tenant and UX updates — docs, webui, storage, tenant service adjustments

* tests: stabilize integration tests + skip external services; fix multi-tenant API behavior and idempotency

- gpt5_nano_compatibility: add pytest-asyncio markers, skip when OPENAI key missing, prevent module-level asyncio.run collection, add conftest
- Ollama tests: add server availability check and skip markers; avoid pytest collection warnings by renaming helper classes
- Graph storage tests: rename interactive test functions to avoid pytest collection
- Document & Tenant routes: support external_ids for idempotency; ensure HTTPExceptions are re-raised
- LightRAG core: support external_ids in apipeline_enqueue_documents and idempotent logic
- Tests updated to match API changes (tenant routes & document routes)
- Add logs and scripts for inspection and audit
2025-12-04 16:04:21 +08:00

152 lines
5.1 KiB
Markdown

# Session Log: Fix Retrieval State Clearing and Tenant Card Statistics
## Date: 2025-12-04
## Summary
Fixed two issues:
1. Retrieval history not being cleared when tenant or KB changes
2. Tenant selection cards showing "0" for KBs, Docs, and GB instead of real figures
## Problem 1: Retrieval State Not Clearing
### Issue
When switching between tenants or knowledge bases, the retrieval chat history persisted, potentially showing results from a different tenant/KB context.
### Root Cause
The `RetrievalTesting.tsx` component did not have an effect hook to clear the messages state when `selectedTenant` or `selectedKB` changed.
### Solution
Added a `useEffect` hook in `RetrievalTesting.tsx` that:
1. Gets both `selectedTenant` and `selectedKB` from `useTenantState`
2. Clears messages state and retrieval history when tenant or KB changes
3. Logs the clearing action for debugging
### Code Changes
**File: `/lightrag_webui/src/features/RetrievalTesting.tsx`**
Added import for `selectedTenant`:
```typescript
const selectedTenant = useTenantState.use.selectedTenant()
const selectedKB = useTenantState.use.selectedKB()
```
Added effect to clear history:
```typescript
// Clear retrieval history when tenant or KB changes to prevent showing stale data
useEffect(() => {
setMessages([])
useSettingsStore.getState().setRetrievalHistory([])
console.log('[RetrievalTesting] Cleared retrieval history due to tenant/KB change:', {
tenant_id: selectedTenant?.tenant_id,
kb_id: selectedKB?.kb_id
})
}, [selectedTenant?.tenant_id, selectedKB?.kb_id])
```
## Problem 2: Tenant Cards Showing Zero Statistics
### Issue
The tenant selection cards displayed "0 KBs", "0 Docs", "0 GB" even when tenants had knowledge bases and documents.
### Root Cause
The `list_tenants` method in `tenant_service.py` was querying the PostgreSQL database but creating `Tenant` objects with default statistics (0, 0, 0.0) instead of computing them from the `knowledge_bases` and `documents` tables.
### Solution
Updated the SQL query in `list_tenants` to use LEFT JOINs to compute:
- `kb_count`: Count of knowledge bases per tenant
- `total_documents`: Count of documents per tenant
- `total_size_bytes`: Sum of file sizes for storage calculation
### Code Changes
**File: `/lightrag/services/tenant_service.py`**
Updated SQL query:
```sql
SELECT
t.tenant_id,
t.name,
t.description,
t.created_at,
t.updated_at,
COALESCE(kb_stats.kb_count, 0) as kb_count,
COALESCE(doc_stats.doc_count, 0) as total_documents,
COALESCE(doc_stats.total_size_bytes, 0) as total_size_bytes
FROM tenants t
LEFT JOIN (
SELECT tenant_id, COUNT(*) as kb_count
FROM knowledge_bases
GROUP BY tenant_id
) kb_stats ON t.tenant_id = kb_stats.tenant_id
LEFT JOIN (
SELECT tenant_id, COUNT(*) as doc_count, COALESCE(SUM(file_size), 0) as total_size_bytes
FROM documents
GROUP BY tenant_id
) doc_stats ON t.tenant_id = doc_stats.tenant_id
ORDER BY t.created_at DESC
```
Updated Tenant object creation to include computed statistics:
```python
tenant = Tenant(
tenant_id=row['tenant_id'],
tenant_name=row['name'],
description=row.get('description', ''),
created_by=None,
metadata={},
kb_count=row.get('kb_count', 0) or 0,
total_documents=row.get('total_documents', 0) or 0,
total_storage_mb=total_storage_mb,
)
```
## Additional Fix: fetchTenants API Compatibility
### Issue
After the tenant service changes, the frontend `fetchTenants` function broke because it expected an array but received a paginated response object.
### Solution
Updated `fetchTenants` in `/lightrag_webui/src/api/tenant.ts` to handle both formats:
```typescript
export async function fetchTenants(): Promise<Tenant[]> {
try {
const response = await apiClient.get('/api/v1/tenants')
const data = response.data
if (Array.isArray(data)) {
return data
}
// New paginated format returns { items: [...], total: N, ... }
return data?.items || []
} catch (error) {
console.error('Failed to fetch tenants:', error)
throw error
}
}
```
## Verification
- ✅ Frontend build passes (TypeScript, Vite)
- ✅ Python syntax check passes
- ✅ Tenant cards now show correct KB count (e.g., "2 KBs" for both tenants)
- ✅ Retrieval history clears when tenant/KB changes (verified via console logs)
- ✅ Empty KB shows proper empty state (no stale retrieval data)
---
## Task Logs
### Actions:
- Added useEffect in RetrievalTesting.tsx to clear messages on tenant/KB change
- Updated SQL query in tenant_service.py to compute real statistics with LEFT JOINs
- Fixed fetchTenants API to handle paginated response format
### Decisions:
- Used LEFT JOINs for statistics to ensure tenants with no KBs or documents still appear
- Used COALESCE for null safety on aggregates
### Next Steps:
- Consider adding refresh button on tenant selection page to update stats
- Monitor for performance impact of JOIN queries on large deployments
### Lessons/Insights:
- When adding new API response formats, ensure backward compatibility in frontend consumers
- Tenant statistics should be computed dynamically from source tables rather than stored as cached values