- Removed runtime mode handling from AIAgentConfigWorkbench and related components.
- Updated tests to reflect changes in AI Agent policy copy and configuration.
- Changed terminology from "workflow" to "revision" in various components and API responses.
- Simplified agent binding logic in channel editing.
- Cleaned up unused variables and types related to runtime modes.
- Updated localization files for consistency with new terminology.
- Added aiAgentWorkflowBindingRepository for managing workflow bindings associated with AI agents.
- Enhanced agentRevisionService to include workflow bindings in agent revisions.
- Updated aIAgentService to handle workflow bindings during agent creation and updates.
- Introduced ai_agent_workflow_binding_service for managing workflow binding logic.
- Created new API endpoints for fetching, creating, updating, and deleting AI workflows.
- Developed a new dashboard page for managing AI workflows.
- Updated frontend components to support workflow binding management in agent configuration.
- Added necessary tests for workflow binding functionality and updated existing tests for compatibility.
- Translated relevant UI texts and messages for workflow management.
- Updated labels in the AI Agents dashboard for clarity, changing "流程状态" to "Playbook 状态" and "未发布流程" to "未发布 Playbook".
- Introduced AI Agent rollout percentage management in channel editing, allowing users to set and rollback rollout percentages.
- Added new API endpoints for rolling back AI Agent rollout and fetching agent run metrics.
- Implemented new UI components for displaying agent run details, including status, duration, and input/output tokens.
- Enhanced type definitions for AdminChannel and AIAgent to include rollout percentages and runtime modes.
- Updated navigation to include a section for agent runs.
- Added new translations for agent run features in both English and Chinese.
- Removed KnowledgeIDs from CreateAIAgentRequest and AIAgentResponse.
- Updated buildAIAgentResponseWithLocale to eliminate knowledge base name retrieval.
- Refactored AI agent repository and service to remove knowledge base handling.
- Adjusted dashboard service to no longer track AI agents without knowledge bases.
- Modified knowledge base service to check for workflow references instead of AI agent references.
- Updated frontend components to remove knowledge base selection and display.
- Enhanced workflow validation to ensure knowledge retrieve nodes have associated knowledge bases.
- Deleted tool_filter_middleware_test.go and tool_helpers.go as they are no longer needed.
- Removed associated test cases in tool_helpers_test.go.
- Refactored knowledge retriever logic by moving it to a new file and updating imports.
- Introduced tooling package for tool result reduction logic.
- Updated traces package to include new trace types and structures.
- Adjusted executor and tool search tool to reflect new package structure.
- Implemented conversation understanding and reply policy execution in the workflow executor.
- Added new node types: NodeTypeConversationUnderstanding and NodeTypeReplyPolicy.
- Enhanced input and output schemas for the new nodes.
- Updated workflow registry to include new node specifications.
- Created tests for the new workflow routes and behaviors.
- Modified existing workflows to integrate the new conversation understanding and reply policy logic.
- Introduced WorkflowConditionBranch and WorkflowNodeConfig types to manage condition branches in nodes.
- Updated NodeConfigPanel and ConditionNodePanel components to support adding, editing, and deleting branches.
- Implemented validation for condition nodes to ensure at least one branch exists and that default branches are correctly configured.
- Modified workflow-utils to handle condition branches and updated toApiDefinition and fromApiDefinition functions to maintain branch integrity during serialization.
- Removed edge condition handling from WorkflowEditor and related components, simplifying edge management.
- Added tests to ensure condition branches are preserved in API definitions.
- Deleted AgentRunLogResponse struct from skill_response.go.
- Removed agent_run_log_repository.go and agent_run_log_service.go files.
- Eliminated AgentRunLogDetailDialog component and its related logic from the dashboard.
- Removed agent run log fetching functions from admin API.
- Updated navigation and localization files to remove references to agent run logs.
- Added ConfigSchema, InputSchema, OutputSchema, and DefaultInputs to AIWorkflowNodeSpecResponse.
- Implemented BuildAIWorkflowNodeSpecs to include variable contracts for start and send_reply nodes.
- Introduced applyAutoInputMappings to automatically map inputs based on node connections.
- Enhanced validation to check for required input mappings in workflows.
- Updated workflow editor to support variable selection for node inputs.
- Translated node names and labels to Chinese for better localization.
- Added tests for variable mapping and validation logic.
- Updated skill handling to use skill IDs instead of skill codes in various components, services, and models.
- Modified tests to reflect changes in skill identification.
- Removed references to skill codes in favor of skill IDs for consistency and clarity.
- Updated localization files to remove skill code references and adjust error messages accordingly.
- Implemented LanceDBProvider for managing vector collections, including methods for creating, deleting, and searching collections.
- Added support for LanceDB configuration in VectorDBConfig.
- Introduced stub for LanceDB provider when not built with the appropriate tag.
- Updated provider initialization to include LanceDB as a supported type.
- Created types and interfaces for vector operations, including Vector, SearchRequest, and SearchResult.
- Added tests for VectorDBConfig unmarshalling and for ensuring proper error handling when LanceDB is not built.
- Updated enums to include LanceDB type and labels.
- Modified frontend enums to reflect the addition of LanceDB.
- Added TitleKey and DescriptionKey fields to ToolSpec for dynamic localization.
- Updated tool specifications to use i18nx for titles, descriptions, and appendices.
- Refactored notification messages to utilize i18nx for localization in conversation and ticket assignment events.
- Improved localization in the debug dialog component for skill definitions.
- Added new translation keys in English and Chinese for ticket and conversation assignment notifications.
- Ensured that fallback messages are properly localized based on user locale.
mlogclub