- Strengthen anti-hallucination rules in extract_triplet prompt to
enforce verbatim-only alias extraction, removing suggestive examples
- Add _extract_deduped_entity_aliases to sync historical aliases from
Neo4j two-stage dedup into PgSQL end_user_info
- Remove unused _fetch_neo4j_user_aliases; reuse injected connector
instead of instantiating new Neo4jConnector
- Simplify _would_merge_cross_role and reuse clean_cross_role_aliases
in _normalize_special_entity_names
- Reuse _USER_PLACEHOLDER_NAMES from dedup module to avoid duplication
- Extract fetch_neo4j_assistant_aliases() into deduped_and_disamb.py as
single source of truth, replacing inline Cypher in write_tools and
extraction_orchestrator
- Normalize USER_PLACEHOLDER_NAMES to lowercase and apply .lower() on
all comparisons to prevent case-variant names leaking into aliases
- Extract user aliases from raw dialog statements instead of post-dedup
entities to bypass merge pollution
- Add alias cross-cleaning step in _normalize_special_entity_names to
strip AI assistant aliases from user entities before dedup
- Call clean_cross_role_aliases after second-layer dedup to handle
historical dirty data merged from Neo4j
- Fix syntax error in prompt_utils.py (ontology_types variable assignment)
- Add speaker context to triplet extraction prompt to distinguish alias ownership
- Add explicit examples and rules in extract_triplet.jinja2 for user vs AI alias attribution
- Introduce cross-role merge protection in dedup (accurate, fuzzy, and LLM stages)
- Normalize special entity names (用户/AI助手) before deduplication
- Add clean_cross_role_aliases() to sanitize aliases before Neo4j write
- Refactor _update_end_user_other_name to merge aliases from PgSQL instead of Neo4j
- Filter AI assistant aliases from user alias extraction in orchestrator
- Add get_thread_safe_redis() function with thread-local storage and PID checking to prevent "Future attached to a different loop" errors in Celery thread and prefork pools
- Implement health_check_interval=30 to prevent stale connection errors after fork
- Uncomment and enable ActivityStatsCache module in cache/memory/__init__.py
- Uncomment ActivityStatsCache implementation in activity_stats_cache.py and update to use get_thread_safe_redis()
- Update interest_memory.py to use thread-safe Redis client
- Update write_tools.py to use thread-safe Redis client
- Remove redundant Chinese comments from aioRedis.py for cleaner code
- Ensures safe Redis operations across different execution contexts and Celery worker configurations
- Remove unauthenticated end_user_controller and its router registration
- Move end user creation logic to authenticated memory_api_controller endpoint
- Add create_end_user method to MemoryAPIService with workspace authorization
- Fix retrieve_nodes import in read_graph to use correct function reference
- Consolidate end user management under authenticated memory API with API key scoping
- 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
