- Added AutoFollowViewport component to automatically scroll to the latest test results.
- Integrated auto-follow functionality into AutoTestLivePanel for improved user experience during test execution.
- Introduced logic to manage following state and handle scroll events effectively.
- Introduced dynamic_variables field in BatchRunCreate schema to support flexible input types.
- Added BatchStartupResult schema to encapsulate startup state, including greeting and auto-confirmed messages.
- Updated BatchRunCaseOut schema to include startup results, enhancing the structure for test run outputs.
- Enhanced test run orchestration to prepare and validate dynamic configurations, ensuring isolated variable management across test cases.
- Implemented changes in the frontend to accommodate new data structures for improved test case execution and result tracking.
- Added support for tracking call end states (pending, speaking, cancelled) in CallEndCoordinator.
- Introduced a callback mechanism for state changes to allow external handling of call end states.
- Updated pipeline and tests to accommodate new state management features, ensuring proper handling of call end scenarios.
- Added support for public Realtime API, including new routes for managing API keys and handling WebRTC connections.
- Introduced RealtimeApiKey model and associated CRUD operations for admin management of API keys.
- Implemented authentication mechanisms for API keys and client secrets.
- Enhanced environment configuration with new secrets for Realtime API.
- Created OpenAIRealtime session management and event processing for real-time interactions.
- Updated schemas and settings to accommodate new features and ensure compatibility with existing systems.
Unify multi-turn behaviors (reply/tool), overall expectation, and input-mode picker while keeping non-text modes as coming soon; batch completed/running use a half-and-half detail panel below the top bar.
Co-authored-by: Cursor <cursoragent@cursor.com>
Add components for batch testing, including BatchRunCompletedView and BatchRunRunningView, to display test results and progress. Introduce BatchCaseStatusBadge and BatchPhasePill for visual status representation. Implement mock data handling for batch run snapshots and case statuses, enhancing the user experience for managing batch tests.
Co-authored-by: Cursor <cursoragent@cursor.com>
Replace the test-cases placeholder with suite list/detail flows, multi-select and drag reorder, and an edit-only single-step reply editor with keyword/LLM assertions.
Co-authored-by: Cursor <cursoragent@cursor.com>
Introduce a new auto test mode in the debug drawer, allowing users to run automated tests with mock data. This includes the addition of AutoTestPanel, AutoTestLivePanel, and AutoTestRunBar components for managing test cases and displaying results. The debug mode can now switch between manual and auto testing, enhancing the debugging experience.
Co-authored-by: Cursor <cursoragent@cursor.com>
Update the 'prompt' field in the Assistant model to use a Text type for improved flexibility. This change is accompanied by a migration script to alter the database schema accordingly.
Add language selection functionality and implement scrollable sections for the ProfilePage. Introduce a new SectionAnchorTabs component for navigation between Webhook and Language sections, improving user experience and organization of settings.
Organize product guides under docs/user and setup/integration under docs/developer, with tabbed navigation for clearer audience targeting.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Theme dropdown: 亮色/暗色/随系统 as one row of three icons
- Prompt editor: sections centered (max-w-7xl) when debug drawer is
closed, full-width aligned with tab edges when open
- Debug drawer opens by default
- Prompt textarea: 8 → 16 rows
Co-Authored-By: Claude <noreply@anthropic.com>
- Added support for managing user transcripts, including pending states and timestamps.
- Implemented methods to handle user transcript completion and deferred assistant messages.
- Updated event handling to ensure user transcripts are emitted before assistant responses.
- Enhanced tests to verify the correct order of transcript and assistant message emissions during user interactions.
- Introduced new utility functions `settingsFromWorkflowGraph` and `workflowGraphWithSettings` to encapsulate settings extraction and graph updates.
- Updated `useWorkflowEditorState` to utilize the new utility functions for improved clarity and maintainability.
- Refactored `AssistantPage` and `WorkflowCanvas` components to leverage the new settings management functions, ensuring consistent handling of workflow settings across the application.
- Removed redundant settings handling code, enhancing overall code cleanliness.
- Extend McpTransport to support "sse" in schemas.
- Refactor McpToolClient to handle both "streamable_http" and "sse" transports.
- Introduce McpServerDialog for managing MCP server configurations, including transport settings and tool synchronization.
- Replace McpServersSection with the new dialog component for improved server management.
- Add tests for MCP transport handling and server dialog functionality.
- Remove the draftAgentPlatform state and related logic, simplifying the creation process for assistant types.
- Default the agent platform to "dify" when creating an assistant of type "智能体平台".
- Replace the platform selection buttons with a ResourceSelectField for improved user experience and maintainability.
- Update the confirmType function to reflect the changes in platform handling.
- Introduce WorkflowAgentStage to manage agent stage configurations and enhance interaction with the workflow engine.
- Implement WorkflowEdgeEvaluator for priority-aware edge evaluation, improving routing decisions based on conditions and user turns.
- Update WorkflowBrain to handle user turns and routing more effectively, ensuring agents cannot have only one default path.
- Enhance CallEndCoordinator to track speech events and manage call termination based on queued speech.
- Add new models and output handling for workflow interactions, improving clarity and maintainability.
- Update tests to validate the new routing logic and agent behavior under various scenarios.
- Update WorkflowBrain to handle greeting playback more effectively, ensuring that the initial greeting completes before transitioning to the first node.
- Introduce new methods for managing greeting states and conditions, enhancing the interaction flow for user turns.
- Refactor WorkflowLLMRouter to improve routing logic and ensure proper handling of conditional paths.
- Enhance tests to verify the correct behavior of greeting management and routing under various scenarios, including waiting for audio playback to finish.
- Update frontend components to reflect changes in edge handling and improve user experience in workflow configurations.
- Remove unused FastGpt and Dify form types, consolidating them into a single AgentPlatformForm.
- Update type definitions and state management to accommodate the new agent platform structure.
- Modify functions to handle agent platform forms and ensure proper integration with existing workflows.
- Enhance assistant type options and update related logic for improved clarity and maintainability.
- Add begin_response and finish_after_current_speech methods to CallEndCoordinator for better management of speech events.
- Update PromptBrain to utilize new methods, ensuring proper handling of generated closing speech and tool-only calls.
- Enhance tests to verify the correct behavior of speech tracking and response handling in various scenarios, including waiting for audio to finish before ending calls.
- Introduce a new test suite for CallEndCoordinator to validate the interaction with speech frames.
- Introduce greeting context handling in BaseBrain and WorkflowBrain to manage assistant greetings effectively.
- Implement prepare_greeting_context method to add greeting messages to the local context while preserving playback order.
- Update pipeline event handling to ensure greeting timestamps are maintained until the client is ready.
- Enhance tests to verify the correct behavior of greeting context management in various scenarios.
- Adjust border radius calculation in GenericNode for better visual consistency.
- Update displayed text in GenericNode to enhance localization by removing the English label.
- Remove unused imports and classes from pipeline.py to streamline the codebase.
- Consolidate dynamic variable handling and workflow management in AssistantPage, enhancing clarity and maintainability.
- Update WorkflowEditor to utilize a more modular approach, improving the overall architecture and reducing complexity.
- Enhance the import structure across components for better organization and readability.
- Implement on_client_ready in BaseBrain to handle client-visible state after the app message channel is ready.
- Extend WorkflowBrain with on_client_ready to replay state that may have been emitted before WebRTC data was ready.
- Update pipeline to call on_client_ready when a client connects.
- Enhance tests to verify the correct behavior of on_client_ready in WorkflowBrain.
- Update ConversationRecorder to include source and nodeId metadata in transcripts for better context tracking.
- Introduce optional variable handling in DynamicVariableStore, allowing for unset variables to be rendered as empty without raising errors.
- Refactor WorkflowBrain to apply turn configurations and manage interaction policies dynamically, improving agent responsiveness.
- Implement tests to ensure proper handling of updated session variables and workflow metadata in various scenarios.
- Introduce WorkflowLLMRouter for pre-response LLM routing, allowing agents to determine the appropriate function to call based on user input.
- Implement UserTurnRoutingProcessor to manage user turns before reaching the LLM, ensuring proper routing and handling of user messages.
- Refactor WorkflowBrain to integrate new routing logic and enhance agent stage configuration, including entry modes and resource management.
- Update service factory to support dynamic LLM resource configuration based on workflow settings.
- Add tests for new routing functionality and ensure proper handling of user messages in various scenarios.
- Introduce RuntimeModelResource and RuntimeKnowledgeBase classes to manage workflow resources.
- Update AssistantConfig to include workflow_model_resources and workflow_knowledge_bases for better integration.
- Refactor validation and processing logic in routes and services to accommodate workflow types.
- Implement dynamic variable support for workflow assistants and enhance graph normalization.
- Add ToolExecutor for reusable tool execution across different assistant types.
- Update various services to ensure compatibility with new workflow features and improve error handling.
Xin Wang