- Delete ExtractionOrchestrator (~2500 lines) and write_tools legacy path;
MemoryService/WritePipeline is now the sole write path
- Remove NEW_PIPELINE_ENABLED feature flag from memory_agent_service
- Simplify pilot_run_service to always use PilotWritePipeline
- Add dialog_at field to statement and triplet extraction prompts as the
primary reference time for resolving relative temporal expressions
- Rewrite relative time phrases (e.g. 昨天, 下周) into concrete dates
directly in statement_text when stably resolvable from dialog_at
- Rename extracat_Pruning.jinja2 to extracat_pruning.jinja2; expand
few-shot examples and update memory type enum (drop NULL, add
agreement/repetition/other)
Remove the deprecated expired_at field from all graph models, Neo4j
Cypher queries, repositories, and pipeline code. Replace with dialog_at
on StatementNode to track the original dialog timestamp.
- Strip expired_at from DialogueNode, ChunkNode, StatementNode,
ExtractedEntityNode, edges, and all Cypher queries
- Add dialog_at to MessageItem schema and propagate through extraction
and graph build steps
- Extract emotion/metadata async submission from WritePipeline into
a generic _submit_celery_task helper
- Add post_store_dedup_and_alias_merge Celery task for async alias
merging and second-layer dedup after Neo4j write
- Switch pytest async backend from anyio to asyncio_mode=auto
- Add valid_at/invalid_at passthrough in triplet extraction prompt (both zh/en)
- Propagate temporal_validity to EntityEntityEdge in ExtractionOrchestrator
- Use coalesce() for valid_at/invalid_at in Neo4j cypher queries to handle NULLs
- Fix workspace_id/config_id UUID parsing in read_memory config resolution
- Downgrade verbose extraction pipeline logs from info to debug
- Remove UUID and short API key patterns from sensitive filter to reduce false positives
- Standardize log message format (use = spacing, end_user_id label)
- Fix misindented TODO comment in write_pipeline.py
- Rename StatementExtractionStep → StatementTemporalExtractionStep and
extract_statement.jinja2 → extract_statement_temporal.jinja2 to reflect
merged temporal extraction logic
- Move extraction_pipeline_orchestrator.py out of steps/ to engine root
- Move dedup_step.py into steps/ directory
- Introduce WriteMemoryRequest schema to replace positional args in write_memory()
- Extract _resolve_and_load_config, _preprocess_files, _write_neo4j, and
_invalidate_interest_cache as private helpers in MemoryAgentService
- Remove shadow pipeline and simplify NEW_PIPELINE_ENABLED branch
- Merge 类型归属/成员隶属/任职服务 relation types into single 归属身份关系 in triplet prompt
- Add alias merge logic (别名属于) in deduplication and MERGE_ALIAS_BELONGS_TO Cypher query
- Add StorageType, Language, MessageItem enums/models to memory_agent_schema
- Reduce AgentMemory_Long_Term.DEFAULT_SCOPE from 6 to 1
- Delete standalone extract_temporal.jinja2 (logic merged into statement step)
Introduce ExtractionStep abstraction with modular pipeline stages:
- Add base ExtractionStep class with render/call/parse lifecycle
- Implement StatementExtractionStep, TripletExtractionStep,
EmbeddingStep, EmotionStep, GraphBuildStep, and DedupStep
- Add SidecarStepFactory for hot-pluggable non-critical steps
- Define Pydantic I/O schemas for all pipeline stages
- Refactor WritePipeline to orchestrate new step-based flow
- Add NEW_PIPELINE_ENABLED env switch for old/new pipeline routing
- Add emotion_enabled config flag to MemoryConfig
- Fix workspace_id reference in get_end_user_connected_config
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)
Corrected variable reference in get_end_user_connected_config log statement. The previous code referenced app.workspace_id which could be incorrect or undefined in this context.
- Replace direct memory agent service calls with unified MemoryService in read endpoint
- Update query preprocessor to use new prompt format and return structured queries
- Enhance MemorySearchResult model with filtering, merging, and ID tracking capabilities
- Add intermediate outputs display for problem split, perceptual retrieval, and search results
- Fix parameter alignment and remove unused history parameter in memory agent service
- Removed try-except block for importing `audit_logger` and directly imported it.
- Removed redundant checks for `audit_logger` being `None` before logging operations.
- Added a check in `MemoryPerceptualService` to return `None` if `model_config` or `llm` is `None`.
- Adjust multi-modal memory write behavior for text and visual data
- Mask API keys in model list response to prevent exposure
- Add capability-based filtering to the model list API
- Add end_user_controller with unauthenticated endpoint for creating end users
- Implement get_or_create_end_user logic to handle duplicate end users by other_id
- Register end_user_controller router in main controller initialization
- Add list_memory_configs endpoint to retrieve all workspace memory configurations
- Update MemoryWriteRequest and MemoryReadRequest to make config_id required field
- Refactor memory API endpoints to parse request body directly instead of using Body parameter
- Add CreateEndUserRequest and CreateEndUserResponse schemas for end user creation
- Add ListConfigsResponse schema for configs listing endpoint
- Remove unused config_id and llm_model_id parameters from Neo4j write operation
- Update .gitignore to exclude redbear-mem-metrics and pitch-deck directories
- Add TODO comment to verify end_user sources (chat, draft, apikey)
- Comment out release validation check to support draft run mode
- Add TODO note explaining temporary fix for draft execution
- Handle null current_release_id in result by returning None instead of failing
- Improve import formatting for MemoryConfig model import statement
- Allow configuration retrieval when app has no published release
* [add]Create a workspace and initialize the default ontology engineering scenario
* [add]The language parameters for creating the workspace determine the default language for switching in the ontology project.
* [changes]Standardized return format
* [add]The default ontology is associated with the default configuration.
* [add]Create a workspace and initialize the default ontology engineering scenario
* [add]The language parameters for creating the workspace determine the default language for switching in the ontology project.
* [changes]Standardized return format
* [add]The default ontology is associated with the default configuration.
- Add workspace_id fallback parameter to memory config loading across all services
- Update hot_memory_tags.py to pass workspace_id when resolving memory configuration
- Enhance emotion_analytics_service.py to support workspace_id as fallback for config resolution
- Improve implicit_memory_service.py with workspace_id fallback in config loading
- Update memory_agent_service.py to handle workspace_id resolution and add refactoring TODO
- Enhance preference_analysis.jinja2 prompt with critical guidance on supporting_evidence extraction
- Add validation to check both config_id and workspace_id before raising configuration errors
- Improve error handling and logging for memory configuration resolution across services
- This enables more flexible memory configuration resolution when config_id is unavailable
- Add null check for actual_config_id before calling term_memory_save in langchain_agent.py to prevent errors when memory config is unavailable
- Add warning log when skipping term_memory_save due to missing memory config
- Fix incorrect attribute reference from memory_config.id to memory_config.config_id in memory_agent_service.py
- Fix method call from private _get_workspace_default_config to public get_workspace_default_config in memory_config_service.py
- Ensures graceful handling of missing memory configurations and prevents runtime errors
* [changes]add user_summary language unification
* [add]Entity extraction, user memory, emotion suggestions, unified language type for writing
* [add]Complete the switch between Chinese and English for the emotion labels and emotion suggestions fields.
* [changes]add user_summary language unification
* [add]Entity extraction, user memory, emotion suggestions, unified language type for writing
* [add]Complete the switch between Chinese and English for the emotion labels and emotion suggestions fields.
* [changes]Modify the code based on the AI review
- Remove get_memory_config_id function from end_user_repository.py as it's no longer needed
- Remove get_end_user_memory_config_id function from memory_agent_service.py to reduce duplication
- Simplify get_end_user_connected_config to use MemoryConfigService.get_config_with_fallback
- Update get_config_with_fallback signature to accept memory_config_id directly instead of end_user_id
- Remove unnecessary AppRelease query and config parsing logic from get_end_user_connected_config
- Streamline memory config retrieval flow to use service layer abstraction
- Improves code maintainability by centralizing config fallback logic in MemoryConfigService
- Add force parameter to delete_config endpoint for controlled deletion of in-use configs
- Implement MemoryConfigService.delete_config with protection against deleting default configs
- Add validation to prevent deletion of configs with connected end-users unless force=True
- Reorganize controller imports to remove duplicates and improve maintainability
- Clean up unused database connection management code from memory_storage_controller
- Add detailed docstring to delete_config endpoint explaining protection mechanisms
- Update error handling with specific BizCode.RESOURCE_IN_USE for configs in active use
- Add comprehensive logging for deletion attempts, warnings, and affected users
- Refactor ConfigParamsDelete schema usage to use MemoryConfigService directly
- Improve API response structure with affected_users count and force_required flag
- Add memory_config_id field to EndUser model for lazy caching of memory configuration
- Create get_end_user_memory_config_id() function for fast retrieval of cached config ID
- Implement lazy update mechanism in get_end_user_connected_config() to cache memory_config_id
- Optimize memory config lookup by storing config ID directly on end_user record
- Improve import organization and formatting in memory_agent_service.py
- Add indexed foreign key relationship to data_config table for efficient queries
* [fix]Fix the interface for statistics of recent activities and applications
* [changes]Modify the code based on the AI review
1.Use the boolean auxiliary methods provided by SQLAlchemy instead of using == True in the is_active filter.
2.The calculation of the "PROJECT_ROOT" has now been hardcoded with five levels of nested os.path.dirname calls.
* [fix]Fix the interface for statistics of recent activities and applications
* [changes]Modify the code based on the AI review
1.Use the boolean auxiliary methods provided by SQLAlchemy instead of using == True in the is_active filter.
2.The calculation of the "PROJECT_ROOT" has now been hardcoded with five levels of nested os.path.dirname calls.
