The form-data validation now ensures all items in the list are of type HttpFormData. Truncation length for embedding inputs is reduced from 8191 to 8000 to accommodate tokenizer differences and avoid overflow. Excel parsing now disables chunking by setting chunk_token_num to 0, aligning with intended behavior for structured file ingestion.
- Updated form-data handling to accept both single FileVariable and ArrayVariable containing FileVariable for file uploads
- Fixed HTTP client redirect handling by enabling follow_redirects=True when downloading remote files
- Adjusted config validation to correctly require list type for form-data fields instead of HttpFormData class
Multiple services were performing individual database queries for FileMetadata when resolving missing file names/sizes. This change batches the queries using `in_()` to reduce database round trips and improve performance.
feat(app): support file metadata in chat messages and DSL app overwrite
- Extended chat message file objects with `name`, `size`, and `file_type` fields across app_chat_service and workflow_service
- Added ability to overwrite existing app configurations via DSL import in app_dsl_service, including type validation and config update logic for AgentConfig, MultiAgentConfig, and WorkflowConfig
- Replace Statement-based implicit memory count (count/3) with actual
MemorySummary node count filtered by DERIVED_FROM_STATEMENT relationship
- Add minimum threshold of 5 MemorySummary nodes before reporting data
- Add _build_empty_profile() to return structured empty profile when
insufficient data exists, skipping unnecessary LLM calls
Added `get_user_by_id_regardless_active` in user repository to support activation/deactivation workflows, updated `user_service` to use it, and refactored `_enrich_release_config` in `app_dsl_service` to accept `default_model_config_id` as a parameter instead of reading from config dict.
- Replace storage_services/search with new read_services/memory_search structure
- Implement content_search and perceptual_search strategies
- Add query_preprocessor for search optimization
- Create memory_service as unified interface
- Update celery_app and graph_search for new architecture
- Add enums for memory operations
- Implement base_pipeline and memory_read pipeline patterns
Align update response with get_end_user_info by extracting profile,
knowledge_tags, and behavioral_hints to top-level keys instead of
returning raw meta_data dict.
Change image_url from required to optional in both operation_tool.py and
tool_service.py for image_understand operation, avoiding parameter validation
conflict with uploaded_files priority logic.
Remove unused operation variable from OpenClawTool.execute().
- 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
OperationTool wraps builtin tools for multi-operation support but did not
forward set_runtime_context, causing OpenClawTool to miss uploaded_files
and conversation_id when used with operation routing.
The knowledge graph retrieval logic in `search.py` was updated to consistently return `DocumentChunk` instances instead of raw dictionaries, improving type safety and alignment with the RAG pipeline's expected data structure. Additionally, debug logging was enhanced in `draft_run_service.py` to log the full `retrieve_chunks_result` before extracting page content, aiding troubleshooting.
Create OpenClawTool class inheriting BuiltinTool with dedicated config
Remove all x-openclaw special handling from CustomTool (~270 lines)
Add multi-operation support (print_task, device_query, image_understand, general)
Change ensure_builtin_tools_initialized to incremental mode for auto-provisioning
Fix OperationTool and LangchainAdapter to support OpenClaw operation routing
