- 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
- Remove unique=True from username column in User model
- Remove username duplicate check in create_user and create_superuser
- Add migration to drop unique index on username, keep email unique
* release/v0.2.8: (23 commits)
[add] migration script
fix(workflow and tool): Output processing modification of tool nodes and error modification for tool tests
feat(workflow): add configurable workflow feature options
fix(web): app features
fix(web): app features
fix(web): app bugfix
fix(web): agent add tools bugfix
fix(web): workflow node ports bugfix
fix(web): my sharing app add empty
fix(app): The bugs that were fixed in the previous version but were later rolled back.
fix(web): app sharing bugfix
fix(app): 1.The end users are still bound to the app. 2. Multi-modal file support includes xlsx, csv, and json. 3. The file routing protocol is consistent with the page routing.
fix(web): audio recorder add max size check
fix(web): max_file_count precision
feat(workflow): expose workflow memory enable status in app share config API
revert(web): file download
fix(perceptual): resolve inconsistency between local filename and actual filename
fix(multimodel): filter unsupported files during perception memory write
fix(web): file download
fix(web): file download
...
1. Increase support for visual models and multimodal models;
2. The application and workflow can input various multimodal files such as images, documents, audio, and videos.
* [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.
1. Three party web website data access - Web site synchronization
Building a knowledge base by crawling web page data in batches through web crawlers
Web site synchronization utilizes crawler technology, which can automatically capture all websites under the same domain name through a single entry website. Currently, it supports up to 200 subpages. For compliance and security reasons, only static site crawling is supported, mainly used for quickly building knowledge bases on various document sites.
2. Feishu Knowledge Base
By configuring Feishu document permissions, a knowledge base can be built using Feishu documents, and the documents will not undergo secondary storage
3. Language Bird Knowledge Base
You can configure the permissions of the language bird document to build a knowledge base using the language bird document, and the document will not undergo secondary storage
1. Add the "Skills" module;
2. The loading of the model square has been modified to be controlled through environment variables;
3. Dynamic scheduling of the skill binding tool;
4. Agent Integration Skills
* [fix]Fix the issue of inconsistent language in explicit and episodic memory.
* [fix]Fix the issue of inconsistent language in explicit and episodic memory.
* [add]Add scene_id
* [fix]Based on the AI review to fix the code
- Add .hypothesis/ to .gitignore for test framework artifacts
- Remove outdated comment from EndUser model memory_config_id field
- Update memory config extraction methods to return tuple with legacy format flag
- Add detection for legacy int-formatted memory_config_id in Agent and Workflow configs
- Implement workspace default memory config fallback when legacy int format detected
- Add _get_workspace_default_memory_config_id method to retrieve default or earliest active config
- Update return types from Optional[uuid.UUID] to Tuple[Optional[uuid.UUID], bool] for extraction methods
- Add comprehensive logging for legacy format detection and fallback behavior
- Improve backward compatibility for applications with old int-based memory configuration data
- 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
