Merge branch 'develop' into feature/20251219_myh
* feature/20251219_myh: (8 commits squashed)
- feat(workflow): update reranker model configuration for knowledge base retrieval
- fix(workflow): fix output issue in parameter extraction node
- fix(workflow): fix output issue in parameter extraction node
- feat(workflow): add user prompt to parameter extraction node
- perf(workflow): change grouped variable input to key-value format in variable aggregator
- feat(workflow): Add new cycle node for iterative workflow execution
- Introduce a new Loop/Iteration node in the workflow engine.
- Supports both conditional loops and iteration over lists.
- Allows parallel execution and flattening of iteration outputs.
- Maintains runtime state, node outputs, and loop variables for downstream nodes.
- Enhances workflow flexibility for complex, repeated operations.
- Merge branch 'develop' into feature/20251219_myh
# Conflicts:
#	api/app/core/workflow/nodes/configs.py
#	api/app/core/workflow/nodes/node_factory.py
- feat(workflow): Add new cycle node for iterative workflow execution
- Introduce a new Loop/Iteration node in the workflow engine.
- Supports both conditional loops and iteration over lists.
- Allows parallel execution and flattening of iteration outputs.
- Maintains runtime state, node outputs, and loop variables for downstream nodes.
- Enhances workflow flexibility for complex, repeated operations.
Signed-off-by: Eternity <1533512157@qq.com>
Reviewed-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>
Reviewed-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>
Merged-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>
CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/78
Add new predicates for learning/education domain to support educational content extraction. Also add field validator to filter empty statements in extraction response to handle malformed LLM outputs.
Add functions related to knowledge base graph:
1. Entity type generation,
2. Knowledge base graph acquisition,
3. Hard deletion of knowledge base graph,
4. Knowledge base graph reconstruction (asynchronous)
1. Optimization of the JSON tool, add insert, replace, delete, parse
2. Optimization of the mcp test_connection
3. tool list desc
4. datetime_tool default timezone set Asia/Shanghai
- 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.
- Add MemoryAPIService with read_memory and write_memory methods for managing user memories
- Create memory_api_schema.py with request/response schemas for read and write operations
- Implement write_memory_api_service endpoint for storing memory content with configurable storage backends
- Implement read_memory_api_service endpoint for querying memories with context-aware responses
- Add memory-specific error codes (MEMORY_WRITE_FAILED, MEMORY_READ_FAILED, MEMORY_CONFIG_NOT_FOUND) to error_codes.py
