- Make MetadataExtractor language param optional (default None) to
support auto-detection fallback when no language is explicitly set
- Refactor clean_metadata from walrus-operator dict comprehension to
explicit loop for correctness and readability
- Remove _replace_first_person_with_user from StatementExtractor to preserve
original user text for downstream metadata/alias extraction
- Delete metadata_utils.py module, inline clean_metadata into Celery task
- Remove unused imports and commented-out collect_user_raw_messages method
- Apply formatting cleanup across metadata models and extraction orchestrator
- Merge alias add/remove into MetadataExtractionResponse and Celery metadata task,
removing the separate sync step from extraction_orchestrator
- Replace first-person pronouns ("我") with "用户" in statement extraction to
preserve identity semantics for downstream metadata/alias extraction
- Update extract_statement.jinja2 prompt to enforce "用户" as subject for user
statements instead of resolving to real names
- Add alias change instructions (aliases_to_add/aliases_to_remove) to
extract_user_metadata.jinja2 with incremental merge logic
- Deduplicate special entities ("用户", "AI助手") in graph_saver by reusing
existing Neo4j node IDs per end_user_id
- Sync final aliases from PgSQL to Neo4j user entity nodes after metadata write
- Remove merge_metadata and its helper functions from metadata_utils.py
- Pass existing_metadata to MetadataExtractor.extract_metadata() as LLM context
- Add merge instructions to extract_user_metadata.jinja2 prompt (zh/en)
- Update Celery task to read existing metadata before extraction and overwrite
- Simplify field descriptions in UserMetadataProfile model
- Add _update_timestamps helper to track changed fields
- Replace version-based optimistic locking and retry loop with apoc.atomic.add/insert for concurrent safety
- Merge duplicate accesses within a batch before updating (access_count_delta)
- Simplify _calculate_update to only compute on new timestamps instead of full history rebuild
- Remove max_retries instance variable (kept as param for backward compat)
- Trim verbose docstrings and inline comments
- Increase max_retries from 3 to 5 for concurrent conflict recovery
- Add randomized exponential backoff between retries to reduce contention
- Merge duplicate node accesses in batch operations to avoid self-conflicts
- Support access_times parameter for merged batch access counting
- Add Community node label support in atomic update content field map
- 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)
- Trigger opening statement on new conversation in run/run_stream
- Fix /opening endpoint to support workflow app type
- Fix features field missing in workflow config release snapshot
- Knowledge node returns citations alongside chunks
- Aggregate citations from all knowledge nodes in result builder
- Filter citations based on features.citation.enabled switch
- Fix WorkflowConfigCreate circular import in app_schema
- 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 memory_config_id extraction and assignment when creating new end users in public share chat
- Introduce get_or_create_end_user_with_config method to handle memory config setup in single transaction
- Add batch_update_memory_config_id_by_app method for bulk updating end user memory configs
- Rename _update_endusers_memory_config_by_workspace to _update_endusers_memory_config_by_app for correct scope
- Update app publish flow to use app_id instead of workspace_id for memory config updates
- Remove unused actual_end_user_id variable in langchain_agent
- Ensures end users are properly associated with memory configs on creation and during app updates
- 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
- Change extract_document_text from private to instance method in multimodal service for external access
- Optimize knowledge base search logic to improve parallel retrieval performance
- 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
