Introduce a layered pipeline architecture for the memory write flow:
- WritePipeline: orchestrates preprocess → extract → store → cluster → summarize
with deadlock retry, resource cleanup, and pilot-run support
- MemoryService: facade that delegates to WritePipeline, placeholder methods
for read/forget/reflect
- BearLogger: structured step-level logging with perf threshold alerts
- Shadow pipeline integration in MemoryAgentService (env-gated pilot run)
Also includes:
- Fix deprecated SQLAlchemy declarative_base import
- Extend Neo4j Entity fulltext index to cover description and aliases
- Migrate Pydantic schemas to v2 (ConfigDict, field_validator)
- Implemented ParameterExtractorNode to extract structured parameters from input text using LLM.
- Supports dynamic Jinja2 prompt rendering with field descriptions and types.
- Integrates with RedBearLLM and ModelConfigService for model retrieval.
- Handles JSON repair and raises clear BusinessException on parsing errors.
