- 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.
- Introduced Qwen-Audio Realtime service for speech-to-speech processing in Pipecat.
- Updated interface catalog to include Qwen-Audio Realtime capabilities.
- Enhanced model resource testing to support new service.
- Added configuration options for audio sample rates and turn detection modes.
- Updated documentation to reflect integration details and usage instructions.
- 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.
- Introduce dynamic variable definitions in AssistantConfig and Assistant models, allowing for flexible prompt customization.
- Implement validation for dynamic variable names and types in the schema.
- Update backend services and routes to handle dynamic variables in assistant configurations and runtime processing.
- Enhance frontend components to support dynamic variable definitions, including a new editor for managing variables.
- Add tests to ensure proper functionality and validation of dynamic variables in various scenarios.
- Introduce new fields for knowledge retrieval configuration in AssistantConfig and Assistant models, including mode, top_n, and score_threshold.
- Implement KnowledgeRetrievalConfig schema with validation for top_n.
- Update backend services and routes to handle knowledge retrieval settings.
- Enhance frontend components to support knowledge retrieval configuration, including a new dialog for advanced settings.
- Add tests for knowledge retrieval configuration validation and description generation.
- Add new models for `KnowledgeDocument` and `KnowledgeChunk` to manage document ingestion and chunking.
- Implement S3-compatible storage integration for knowledge documents, allowing for file uploads and retrieval.
- Introduce API endpoints for managing knowledge bases and documents, including creation, deletion, and searching.
- Update frontend components to support knowledge base configuration and document management, improving user interaction.
- Enhance backend services for knowledge processing and retrieval, ensuring robust handling of document statuses and errors.
- Introduce a new `turnConfig` field in `AssistantConfig` and `Assistant` models to manage user interaction settings.
- Implement `TurnConfig`, `BargeInConfig`, `VadConfig`, and `TurnDetectionConfig` schemas to define turn management strategies.
- Update the backend to handle turn configuration in the database and during assistant operations.
- Enhance frontend components with a `TurnConfigEditor` for configuring turn settings, including VAD and barge-in strategies.
- Modify existing pages to integrate turn configuration, improving user experience and interaction capabilities.
- Introduce new fields `dify_api_url` and `dify_api_key` in `AssistantConfig` for Dify API integration.
- Update `requirements.txt` to include `dify-client-python` for Dify SDK support.
- Modify `config_resolver` to handle Dify connection information.
- Add a new `globalNode` type in workflow specifications to provide unified settings across workflows.
- Enhance node specifications with additional constraints and default values for better configuration management.
- Update frontend components to support the new `globalNode` type and its properties, improving workflow editor functionality.
- Introduce new database models for conversation sessions, messages, and artifacts to support conversation history tracking.
- Implement API routes for listing conversations and retrieving detailed conversation data, enhancing user interaction with historical records.
- Add a conversation recorder service to persist conversation messages in real-time without disrupting ongoing calls.
- Update the frontend to display conversation history, including filtering and sorting options, improving user experience.
- Enhance the pipeline to integrate conversation history recording seamlessly during interactions.
- Introduce a new `RuntimeTool` model to encapsulate tool data for runtime sessions, including attributes like `id`, `name`, `function_name`, `type`, and `description`.
- Update the `AssistantConfig` model to include a list of reusable tools, allowing for better management of tools within assistant configurations.
- Modify the `config_resolver` service to fetch and resolve tools associated with assistants, ensuring they are available during runtime.
- Refactor tool-related CRUD operations in the `tools` route to support the new runtime execution model, enhancing the overall tool management system.
- Update documentation and comments to reflect changes in tool execution and configuration handling, improving clarity for future development.
- Replace the `config.py` module with a new `settings.py` to streamline environment variable management, focusing on database, CORS, and TURN settings.
- Update references throughout the backend codebase to use the new `settings` module instead of the deprecated `config`.
- Modify the `.env.example` file to reflect the new configuration approach, indicating that model provider credentials should be maintained separately.
- Enhance the `AssistantConfig` model to clarify the source of runtime connection information, ensuring it is injected from model resources rather than relying on defaults from the environment.
- Introduce new user scripts for audio and video management in the Tampermonkey environment, enhancing WebRTC capabilities.
- Update `requirements.txt` to include Pillow for image handling.
- Refactor vision model validation logic in `voice_webrtc.py` to improve error handling for unsupported image input.
- Introduce new functions in `pipeline.py` for image data processing and analysis using vision models.
- Implement `VisionCaptureProcessor` to manage video frame requests for auxiliary vision model analysis.
- Enhance the pipeline to support image input requests and integrate vision model responses into the processing flow.
- Introduce a new `support_image_input` field in model resources, allowing models to indicate support for image input.
- Update the backend models, schemas, and database seed scripts to accommodate the new field.
- Enhance the AssistantConfig and related routes to handle image input capabilities, ensuring proper validation and error handling.
- Modify the frontend components to include toggles for enabling visual understanding and filtering models based on image input support.
- Implement necessary adjustments in the voice preview and pipeline to integrate video stream handling alongside audio functionalities.
- Add new fields in AssistantConfig for FastGPT connection details, including `fastgpt_api_url`, `fastgpt_api_key`, and `fastgpt_app_id`.
- Update the pipeline to utilize the new FastGPT configuration, ensuring proper integration with external services.
- Introduce type handling for different assistant types, including support for realtime modes and external brain management.
- Refactor frontend components to include hints for FastGPT configuration inputs, improving user guidance during setup.
- Introduce mechanisms in the pipeline to ensure that the end call process waits for the completion of the end speech before hanging up, improving user experience during call termination.
- Update the useVoicePreview hook to handle server-initiated call endings gracefully, distinguishing between normal and error disconnections.
- Adjust TTS stop frame timeout settings to optimize the timing of call terminations, ensuring timely responses without unnecessary delays.
- Refactor related components to support the new end call logic, enhancing overall workflow management and user interaction.
- Introduce edge transition speech functionality in the WorkflowEngine to provide optional speech during node transitions.
- Update pipeline execution to utilize the new transition speech feature, enhancing user experience by masking delays during transitions.
- Modify frontend components to support transition speech in edge specifications, allowing users to define and edit transition speech for edges.
- Refactor edge handling logic in the WorkflowEditor to accommodate the new transition speech field, improving workflow management capabilities.
- Introduce a new WorkflowEngine class to manage workflow graphs, enabling dynamic node-based interactions.
- Update AssistantConfig to include a graph field for workflow definitions, allowing for flexible configuration.
- Modify pipeline execution to support workflow-driven dialogue, integrating node transitions and system prompts based on active nodes.
- Enhance frontend components to visualize active nodes and provide debugging capabilities, including highlighting the current node during interactions.
- Refactor existing components to accommodate new workflow functionalities and improve overall user experience.
- Add new fields to AssistantConfig for realtime interface configuration, including types, values, and secrets.
- Introduce StepFunRealtimeService to handle speech-to-speech processing via WebSocket, integrating STT, LLM, and TTS functionalities.
- Refactor pipeline execution to support a new realtime mode, allowing direct text input processing and immediate responses.
- Update model resource testing to include validation for StepFun Realtime connections.
- Enhance service factory to create realtime services based on configuration settings.
- Modify README documentation to reflect new realtime capabilities and usage instructions.
Xin Wang