* [fix]The repair model does not allow null values and does not support relational networks.
* [fix]The repair model does not allow null values and does not support relational networks.
* [changes]Restore field restrictions
- Add top margin (rb:mt-2) to bottom label in ChatContent for better spacing
- Wrap Chat component in centered container with max-width (760px) and top padding
- Replace AnalysisEmptyIcon with BgImg in empty state for improved visual consistency
- Add size prop [320,180] to Empty component for proper empty state dimensions
- Adjust contentClassName spacing for better layout alignment
- Improves overall chat interface visual hierarchy and spacing consistency
- Remove template_service extraction and template rendering logic
- Remove LLM client initialization from MemoryClientFactory
- Remove structured response call to LLM with RetrieveSummaryResponse model
- Replace LLM-based answer generation with direct retrieval information
- Simplify response to use raw retrieved info or default fallback message
- Update logging to reflect non-LLM quick answer approach
- Reduce unnecessary dependencies and improve performance by eliminating LLM call overhead
* [refactor]Reconstructing forgotten, emotional, situational, and explicit memory statistics
* [refactor]Reconstructing forgotten, emotional, situational, and explicit memory statistics
* [changes]Improve the code based on AI review
* [changes]Statistics on work, perception, short-term, and implicit memory
* [changes]Statistics on work, perception, short-term, and implicit memory
* [changes]Replace the invisible memory calculation method
* [changes]Statistics on work, perception, short-term, and implicit memory
* [refactor]Reconstructing forgotten, emotional, situational, and explicit memory statistics
* [changes]Statistics on work, perception, short-term, and implicit memory
* [changes]Replace the invisible memory calculation method
- Extract port markup and attributes to shared constants for reusability
- Add text label support to ports with '+' symbol and styling
- Update port radius from 4 to 6 pixels for better visibility
- Remove duplicate port configuration definitions from hook
- Replace all port group definitions to use centralized portMarkup and portAttrs
- Update edge connector to use smooth curve styling
- Change edge target marker from block to diamond shape
- Consolidate port styling logic to reduce code duplication and improve maintainability
- Add [PERF] prefixed logging throughout hybrid search pipeline for better performance visibility
- Break down latency metrics with separate timing for config loading, embedder initialization, and rerank computation
- Format latency breakdown as JSON in performance summary logs
- Optimize batch_record_access to process node access records in parallel using asyncio.gather instead of sequential processing
- Add performance timing instrumentation for forgetting config loading and rerank computation stages
- Reorganize imports in access_history_manager for consistency
- Improve observability of search performance bottlenecks through structured logging
