- Changed the module name for form extraction to "更新表单" for clarity.
- Enhanced the extraction process to accommodate various output formats from nodes, ensuring compatibility with different structures.
- Improved handling of empty or invalid form updates, returning an empty object when necessary to maintain robustness.
- Introduced a normalization function for client mode to default to "direct" when input is empty or None.
- Updated the clientMode field to use a new type with BeforeValidator for improved validation.
- Added a test to ensure empty client mode inputs correctly default to "direct".
- Updated documentation and API endpoint to include a new state code '0005' for handling cases where photo recognition fails consecutively, directing to human assistance.
- Ensured consistency between documentation and code for improved clarity in state management.
- Introduced a new function to extract the first state code and clean content by removing state tags.
- Updated the chat endpoint to utilize the new extraction function, improving state handling and content processing.
- Enhanced logging to provide clearer insights into extracted state codes and cleaned content.
- Moved SentenceTextChunker and SentenceTextChunkerConfig to the utils module for better organization.
- Updated pytest.ini to include the current directory in the Python path.
- Added a new utils module with shared utility helpers.
- Adjusted import paths in the test files to reflect the new location of text chunking classes.
- Introduced SentenceTextChunker and SentenceTextChunkerConfig for improved text processing in chat responses.
- Updated chat endpoint to conditionally use text chunking based on the new 'useTextChunk' parameter from the request.
- Enhanced logging to include 'useTextChunk' status and adjusted text delta handling to support chunked responses.
- Modified ProcessRequest_chat model to include 'useTextChunk' field for request handling.
- Added unit tests for SentenceTextChunker to ensure correct chunking behavior and edge case handling.
- Added detailed logging for chat request processing, including session ID, input text length, and latency measurements.
- Implemented performance tracking for streaming events, capturing first event and text delta timings.
- Improved error handling logging to include session context and duration on failures.
- Updated non-stream response logging to include latency and output details for better debugging.
- Introduced a new function to parse JSON values in endpoints.py for improved data handling.
- Updated extract_form_update_from_flow_nodes to return structured data instead of strings.
- Changed formUpdate field in ProcessResponse_chat model to use Any type with a default empty dictionary for better flexibility in handling updates.
- Changed ANALYSIS_SERVICE_URL to localhost for local development.
- Updated ANALYSIS_AUTH_TOKEN and APP_ID for improved security.
- Added new functions in endpoints.py for form extraction and stage code normalization.
- Enhanced chat handling to support form updates and improved event streaming.
- Updated models to include new fields for form update handling.
- Added support for UserStartedSpeakingFrame to enhance user interaction tracking.
- Updated the pipeline to reset idle prompt count when a user starts speaking, improving responsiveness during conversations.
- Integrated new event handlers for better management of user turn events and upstream frame processing.
- Added idle prompt timeout, maximum count, and text to multiple voice configuration files to improve user interaction during idle periods.
- Updated greeting mode to 'fastgpt_opener' in relevant configurations for a more dynamic greeting experience.
- Introduced a new voice configuration file for xfyun TTS, including detailed service settings and parameters.
- Refactored the pipeline to handle idle prompts and user turn events, ensuring smoother interaction flow.
- Adjusted the VAD and turn configurations to accommodate new idle prompt features.
Parse leading <state> tags from LLM replies and emit response.state over the product websocket while stripping tags from TTS/text streams. Add FastGPT+Xfyun voice configs (including state-enabled preset), SuperTTS support, and context sync for interrupted turns. Refresh the voice demo with a state indicator and collapsible audio delta websocket log groups.
Co-authored-by: Cursor <cursoragent@cursor.com>
Xin Wang